Dear Editor,This letter proposes an end-to-end feature disentangled Transformer(FDTs)for entanglement-free and semantic feature representation to enable accurate and trustworthy pathology grading of squamous cell carc...Dear Editor,This letter proposes an end-to-end feature disentangled Transformer(FDTs)for entanglement-free and semantic feature representation to enable accurate and trustworthy pathology grading of squamous cell carcinoma(SCC).Existing vision transformers(ViTs)can implement representation learning for SCC grading,however,they all adopt the class-patch token fuzzy mapping for pattern prediction probability or window down-sampling to enhance the representation to contextual information.展开更多
Deep neural networks(DNNs)and generative AI(GenAI)are increasingly vulnerable to backdoor attacks,where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels.Beyond tradit...Deep neural networks(DNNs)and generative AI(GenAI)are increasingly vulnerable to backdoor attacks,where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels.Beyond traditional single-trigger scenarios,attackers may inject multiple triggers across various object classes,forming unseen backdoor-object configurations that evade standard detection pipelines.In this paper,we introduce DBOM(Disentangled Backdoor-Object Modeling),a proactive framework that leverages structured disentanglement to identify and neutralize both seen and unseen backdoor threats at the dataset level.Specifically,DBOM factorizes input image representations by modeling triggers and objects as independent primitives in the embedding space through the use of Vision-Language Models(VLMs).By leveraging the frozen,pre-trained encoders of VLMs,our approach decomposes the latent representations into distinct components through a learnable visual prompt repository and prompt prefix tuning,ensuring that the relationships between triggers and objects are explicitly captured.To separate trigger and object representations in the visual prompt repository,we introduce the trigger–object separation and diversity losses that aids in disentangling trigger and object visual features.Next,by aligning image features with feature decomposition and fusion,as well as learned contextual prompt tokens in a shared multimodal space,DBOM enables zero-shot generalization to novel trigger-object pairings that were unseen during training,thereby offering deeper insights into adversarial attack patterns.Experimental results on CIFAR-10 and GTSRB demonstrate that DBOM robustly detects poisoned images prior to downstream training,significantly enhancing the security of DNN training pipelines.展开更多
Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,th...Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,the existing generative image steganography methods generally have good steganography performance,but there is still potential room for enhancing both the quality of stego images and the accuracy of secret information extraction.Therefore,this paper proposes a generative image steganography algorithm based on attribute feature transformation and invertible mapping rule.Firstly,the reference image is disentangled by a content and an attribute encoder to obtain content features and attribute features,respectively.Then,a mean mapping rule is introduced to map the binary secret information into a noise vector,conforming to the distribution of attribute features.This noise vector is input into the generator to produce the attribute transformed stego image with the content feature of the reference image.Additionally,we design an adversarial loss,a reconstruction loss,and an image diversity loss to train the proposed model.Experimental results demonstrate that the stego images generated by the proposed method are of high quality,with an average extraction accuracy of 99.4%for the hidden information.Furthermore,since the stego image has a uniform distribution similar to the attribute-transformed image without secret information,it effectively resists both subjective and objective steganalysis.展开更多
By taking into account spatial degrees of freedom of atoms, we study the internal-state disentanglement dynamics of two atoms interacting with a vacuum multi-mode noise field. We show that the complete internal-state ...By taking into account spatial degrees of freedom of atoms, we study the internal-state disentanglement dynamics of two atoms interacting with a vacuum multi-mode noise field. We show that the complete internal-state disentanglement of the two atoms, caused due to the atomic spontaneous emission can be achieved in a finite time.展开更多
Learning disentangled representation of data is a key problem in deep learning.Specifically,disentangling 2D facial landmarks into different factors(e.g.,identity and expression)is widely used in the applications of f...Learning disentangled representation of data is a key problem in deep learning.Specifically,disentangling 2D facial landmarks into different factors(e.g.,identity and expression)is widely used in the applications of face reconstruction,face reenactment and talking head et al..However,due to the sparsity of landmarks and the lack of accurate labels for the factors,it is hard to learn the disentangled representation of landmarks.To address these problem,we propose a simple and effective model named FLD-VAE to disentangle arbitrary facial landmarks into identity and expression latent representations,which is based on a Variational Autoencoder framework.Besides,we propose three invariant loss functions in both latent and data levels to constrain the invariance of representations during training stage.Moreover,we implement an identity preservation loss to further enhance the representation ability of identity factor.To the best of our knowledge,this is the first work to end-to-end disentangle identity and expression factors simultaneously from one single facial landmark.展开更多
The disentanglement evolution of bipartite spin-1/2 system coupled to a common surrounding XY chain in transverse fields at nonzero temperature is studied in this letter. The dynamical process of the entanglement is n...The disentanglement evolution of bipartite spin-1/2 system coupled to a common surrounding XY chain in transverse fields at nonzero temperature is studied in this letter. The dynamical process of the entanglement is numerically and analytically investigated. We find that thermal effects can enhance disentanglement if the entangled initial state of the central spins does not in the decoherence free space. The critical phenomenon of quantum phase transitions reflected in the disentanglement can be washed out by the thermal effect eventually.展开更多
We investigate the entanglement evolution of two qubits that are initially in Werner state under the classical phase noise. We discuss the influence of mixture degree on disentanglement. It is showed that the more mix...We investigate the entanglement evolution of two qubits that are initially in Werner state under the classical phase noise. We discuss the influence of mixture degree on disentanglement. It is showed that the more mixed the state, the shorter is the time of disentanglement.展开更多
A straightforward simple proof is given that dark energy is the natural conse-quence of a quantum disentanglement physical process. Thus while the ordinary energy density of the cosmos is equal to half that of Hardy’...A straightforward simple proof is given that dark energy is the natural conse-quence of a quantum disentanglement physical process. Thus while the ordinary energy density of the cosmos is equal to half that of Hardy’s quantum probability of Entanglement i.e. where , the density of cosmic dark energy is consequently one minus divided by two i.e. . This result is in full agreement with all the numerous previous theoretical predictions as well as being in remarkable agreement with the overwhelming majority of cosmic accurate measurements and observations.展开更多
We analyze the spin coincidence experiment considered by Bell in the derivation of Bells theorem. We solve the equation of motion for the spin system with a spin Hamiltonian, Hz, where the magnetic field is only in th...We analyze the spin coincidence experiment considered by Bell in the derivation of Bells theorem. We solve the equation of motion for the spin system with a spin Hamiltonian, Hz, where the magnetic field is only in the z-direction. For the specific case of the coincidence experiment where the two magnets have the same orientation the Hamiltonian Hz commutes with the total spin Iz, which thus emerges as a constant of the motion. Bells argument is then that an observation of spin up at one magnet A necessarily implies spin down at the other B. For an isolated spin system A-B with classical translational degrees of freedom and an initial spin singlet state there is no force on the spin particles A and B. The spins are fully entangled but none of the spin particles A or B are deflected by the Stern-Gerlach magnets. This result is not compatible with Bells assumption that spin 1/2 particles are deected in a Stern-Gerlach device. Assuming a more realistic Hamiltonian Hz + Hx including a gradient in x direction the total Iz is not conserved and fully entanglement is not expected in this case. The conclusion is that Bells theorem is not applicable to spin coincidence measurement originally discussed by Bell.展开更多
Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation....Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation. Disentangled GCNs have been proposed to divide each node’s representation into several feature units. However, current disentangling methods do not try to figure out how many inherent factors the model should assign to help extract the best representation of each node. This paper then proposes D^(2)-GCN to provide dynamic disentanglement in GCNs and present the most appropriate factorization of each node’s mixed features. The convergence of the proposed method is proved both theoretically and experimentally. Experiments on real-world datasets show that D^(2)-GCN outperforms the baseline models concerning node classification results in both single- and multi-label tasks.展开更多
In the field of brain decoding research,reconstructing visual perception from neural recordings is a challenging but crucial task.With the use of superior algorithms,many methods have been dedicated to enhancing decod...In the field of brain decoding research,reconstructing visual perception from neural recordings is a challenging but crucial task.With the use of superior algorithms,many methods have been dedicated to enhancing decoding performance.However,these models that map neural activities onto semantically entangled feature space are difficult to interpret.It is hard to understand the connections between neural activities and these abstract features.In this paper,we propose an interpretable neural decoding model that projects neural activities onto a semantically disentangled feature space with each dimension representing distinct visual attributes,such as gender and facial pose.A two-stage algorithm is designed to achieve this goal.First,a deep generative model learns semantically-disentangled image representations in an unsupervised way.Second,neural activities are linearly embedded into the semantic space,which the generator uses to reconstruct visual stimuli.Due to modality heterogeneity,it is challenging to learn such a neural embedded high-level semantic representation.We induce pixel,feature,and semantic alignment to ensure reconstruction quality.Three experimental fMRI datasets containing handwritten digits,characters,and human face stimuli are used to evaluate the neural decoding performance of our model.We also demonstrate the model interpretability through a reconstructed image editing application.The experimental results indicate that our model maintains a competitive decoding performance while remaining interpretable.展开更多
Maximally-localized Wannier functions(MLWFs)are widely employed as an essential tool for calculating the physical properties of materials due to their localized nature and computational efficiency.Projectability-disen...Maximally-localized Wannier functions(MLWFs)are widely employed as an essential tool for calculating the physical properties of materials due to their localized nature and computational efficiency.Projectability-disentangled Wannier functions(PDWFs)have recently emerged as a reliable and efficient approach for automatically constructing MLWFs that span both occupied and lowest unoccupied bands.Here,we extend the applicability of PDWFs to magnetic systems and/or those including spin-orbit coupling,and implement such extensions in automated workflows.Furthermore,we enhance the robustness and reliability of constructing PDWFs by defining an extended protocol that automatically expands the projectors manifold,when required,by introducing additional appropriate hydrogenic atomic orbitals.We benchmark our extended protocol on a set of 200 chemically diverse materials,as well as on the 40 systems with the largest band distance obtained with the standard PDWF approach,showing that on our test set the present approach delivers a success rate of over 98%in obtaining accurate Wannier-function interpolations,defined as an average band distance below20 meV between the DFT and Wannier-interpolated bands,up to 2 eV above the Fermi level for metals or above the conduction band minimum for insulators(and a 100%success rate when including only bands up to 1 eV above these values).展开更多
1 Introduction Molecular Property Prediction aims to identify molecules sharing similar efficacious properties[1],which is a foundational task in drug discovery,materials science and bioinformatics.Graph neural networ...1 Introduction Molecular Property Prediction aims to identify molecules sharing similar efficacious properties[1],which is a foundational task in drug discovery,materials science and bioinformatics.Graph neural networks(GNNs)have shown significant success in this field.However,GNN-based methods often face label scarcity,limiting their performance in predicting molecular properties.Besides,GNNs trained on specific datasets frequently struggle with generalization due to domain shift[2].展开更多
Shear stress overshoot in entangled polymer rheology is a hallmark of transient dynamics,but its microscopic origin remains under debate.Using molecular dynamics simulations,we investigate a two-step shear protocol co...Shear stress overshoot in entangled polymer rheology is a hallmark of transient dynamics,but its microscopic origin remains under debate.Using molecular dynamics simulations,we investigate a two-step shear protocol consisting of successive startup shears separated by a waiting period,with the first shear interrupted before the overshoot.In the homogeneous flow,the GLaMM theory captures the stress response during the first shear,but fails to reproduce the nonmonotonic dependence of the second stress overshoot(σ_(2max))on the waiting time.Contrary to the prediction of a nonmonotonic normal stress component σ_(yy)during the waiting period,our simulations show that σ_(yy),like the tube segment orientation(S_(xy)),the contour length of the primitive chain(L),and the entanglement number per chain(Z),relaxes monotonically toward equilibrium.At the strain corresponding to σ_(2max),both the tube segment orientation and the entanglement number per chain exhibit a nonmonotonic dependence on the waiting time that closely mirrors the behavior of σ_(2max),indicating that both factors play significant roles in governing(σ_(2max).Our findings are consistent with the interpretation of lanniruberto and Ma rrucci[ACS Macro.Lett.2014,3,552]for orientation effects and with the viewpoint of Wang et al.[Macromolecules 2013,46,3147]for entanglement effects,although the two explanations are rooted in distinct physical pictu res.These results provide new insights into the stress responses of entanglement polymer fluids and underscore the need for a more unified theoretical framework.展开更多
The capability of Convolutional Neural Networks(CNNs)for sparse representation has significant application to complex tasks like Representation Learning(RL).However,labelled datasets of sufficient size for learning th...The capability of Convolutional Neural Networks(CNNs)for sparse representation has significant application to complex tasks like Representation Learning(RL).However,labelled datasets of sufficient size for learning this representation are not easily obtainable.The unsupervised learning capability of Variational Autoencoders(VAEs)and Generative Adversarial Networks(GANs)provide a promising solution to this issue through their capacity to learn representations for novel data samples and classification tasks.In this research,a texture-based latent space disentanglement technique is proposed to enhance learning of representations for novel data samples.A comparison is performed among different VAEs and GANs with the proposed approach for synthesis of new data samples.Two different VAE architectures are considered,a single layer dense VAE and a convolution based VAE,to compare the effectiveness of different architectures for learning of the representations.The GANs are selected based on the distance metric for disjoint distribution divergence estimation of complex representation learning tasks.The proposed texture-based disentanglement has been shown to provide a significant improvement for disentangling the process of representation learning by conditioning the random noise and synthesising texture rich images of fruit and vegetables。展开更多
A complete ecosystem is also a complex network in which multifarious species interact with each other to achieve system-level functions, such as nutrient biogeochemistry (1)Microbial community is commonly considered a...A complete ecosystem is also a complex network in which multifarious species interact with each other to achieve system-level functions, such as nutrient biogeochemistry (1)Microbial community is commonly considered as the primary driving force of ecosystem nutrient mobilization and metabolism, especially carbon (C), nitrogen (N), phosphorus (P), sulfur (S) and methane coupling process (2)The rise of metagenomics and high-throughput array (e.g. PhyloChip, GeoChip, etc.展开更多
The dynamics of the center-of-mass of entangled polymer is assumed to be of 1-dimen-sional Brownian motion in a constrained tube. When the length fluctuation of the constrain-ed tube is neglected, the asymptotic relat...The dynamics of the center-of-mass of entangled polymer is assumed to be of 1-dimen-sional Brownian motion in a constrained tube. When the length fluctuation of the constrain-ed tube is neglected, the asymptotic relation between the relaxation time for disentangle-ment τ and the chain length N is obtained, i.e. τ～N^3. Under conditions of the finite chainlength and the length fluctuation of an effective constrained tube, the dependence relation τ～N^(3.40±0.16) is obtained by computer simulation. This conclusion elucidates reasonably the knownexperimental results about the dynamics of real entangled polymers.展开更多
Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict relations.However,subgraphs may contain disconn...Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict relations.However,subgraphs may contain disconnected regions,which usually represent different semantic ranges.Because not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic aggregation.To indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are updated.The disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph structures.Furthermore,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the subgraphs.Experimentally,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@10.Experiments prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.展开更多
representation that can identify and isolate different potential variables hidden in the highdimensional observations.Disentangled representation learning can capture information about a single change factor and contr...representation that can identify and isolate different potential variables hidden in the highdimensional observations.Disentangled representation learning can capture information about a single change factor and control it by the corresponding potential subspace,providing a robust representation for complex changes in the data.In this paper,we first introduce and analyze the current status of research on disentangled representation and its causal mechanisms and summarize three crucial properties of disentangled representation.Then,disentangled representation learning algorithms are classified into four categories and outlined in terms of both mathematical description and applicability.Subsequently,the loss functions and objective evaluation metrics commonly used in existing work on disentangled representation are classified.Finally,the paper summarizes representative applications of disentangled representation learning in the field of remote sensing and discusses its future development.展开更多
In recent years,the concept of digital human has attracted widespread attention from all walks of life,and the modelling of high-fidelity human bodies,heads,and hands has been intensively studied.This paper focuses on...In recent years,the concept of digital human has attracted widespread attention from all walks of life,and the modelling of high-fidelity human bodies,heads,and hands has been intensively studied.This paper focuses on head modelling and proposes a generic head parametric model based on neural radiance fields.Specifically,we first use face recognition networks and 3D facial expression database FaceWarehouse to parameterize identity and expression semantics,respectively,and use both as conditional inputs to build a neural radiance field for the human head,thereby improving the head model’s representation ability while ensuring editing capabilities for the identity and expression of the rendered results;then,through a combination of volume rendering and neural rendering,the 3D representation of the head is rapidly rendered into the 2D plane,producing a high-fidelity image of the human head.Thanks to the well-designed loss functions and good implicit representation of the neural radiance field,our model can not only edit the identity and expression independently,but also freely modify the virtual camera position of the rendering results.It has excellent multi-view consistency,and has many applications in novel view synthesis,pose driving and more.展开更多
基金supported by the National Natural Science Foundation of China(62272078)the Chongqing Natural Science Foundation(CSTB2023NSCQ-LZX0069).
文摘Dear Editor,This letter proposes an end-to-end feature disentangled Transformer(FDTs)for entanglement-free and semantic feature representation to enable accurate and trustworthy pathology grading of squamous cell carcinoma(SCC).Existing vision transformers(ViTs)can implement representation learning for SCC grading,however,they all adopt the class-patch token fuzzy mapping for pattern prediction probability or window down-sampling to enhance the representation to contextual information.
基金supported by the UWF Argo Cyber Emerging Scholars(ACES)program funded by the National Science Foundation(NSF)CyberCorps^(®) Scholarship for Service(SFS)award under grant number 1946442.
文摘Deep neural networks(DNNs)and generative AI(GenAI)are increasingly vulnerable to backdoor attacks,where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels.Beyond traditional single-trigger scenarios,attackers may inject multiple triggers across various object classes,forming unseen backdoor-object configurations that evade standard detection pipelines.In this paper,we introduce DBOM(Disentangled Backdoor-Object Modeling),a proactive framework that leverages structured disentanglement to identify and neutralize both seen and unseen backdoor threats at the dataset level.Specifically,DBOM factorizes input image representations by modeling triggers and objects as independent primitives in the embedding space through the use of Vision-Language Models(VLMs).By leveraging the frozen,pre-trained encoders of VLMs,our approach decomposes the latent representations into distinct components through a learnable visual prompt repository and prompt prefix tuning,ensuring that the relationships between triggers and objects are explicitly captured.To separate trigger and object representations in the visual prompt repository,we introduce the trigger–object separation and diversity losses that aids in disentangling trigger and object visual features.Next,by aligning image features with feature decomposition and fusion,as well as learned contextual prompt tokens in a shared multimodal space,DBOM enables zero-shot generalization to novel trigger-object pairings that were unseen during training,thereby offering deeper insights into adversarial attack patterns.Experimental results on CIFAR-10 and GTSRB demonstrate that DBOM robustly detects poisoned images prior to downstream training,significantly enhancing the security of DNN training pipelines.
基金supported in part by the National Natural Science Foundation of China(Nos.62202234,62401270)the China Postdoctoral Science Foundation(No.2023M741778)the Natural Science Foundation of Jiangsu Province(Nos.BK20240706,BK20240694).
文摘Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,the existing generative image steganography methods generally have good steganography performance,but there is still potential room for enhancing both the quality of stego images and the accuracy of secret information extraction.Therefore,this paper proposes a generative image steganography algorithm based on attribute feature transformation and invertible mapping rule.Firstly,the reference image is disentangled by a content and an attribute encoder to obtain content features and attribute features,respectively.Then,a mean mapping rule is introduced to map the binary secret information into a noise vector,conforming to the distribution of attribute features.This noise vector is input into the generator to produce the attribute transformed stego image with the content feature of the reference image.Additionally,we design an adversarial loss,a reconstruction loss,and an image diversity loss to train the proposed model.Experimental results demonstrate that the stego images generated by the proposed method are of high quality,with an average extraction accuracy of 99.4%for the hidden information.Furthermore,since the stego image has a uniform distribution similar to the attribute-transformed image without secret information,it effectively resists both subjective and objective steganalysis.
基金Supported by Foundation of the Education Department of Liaoning Province under Grant No.20060160the Natural Science Foundation of Zhejiang Province under Grant No.Y6100098+1 种基金the National Natural Scinece Foundation of China under Grant No.11074062the funding support from Hangzhou Normal University
文摘By taking into account spatial degrees of freedom of atoms, we study the internal-state disentanglement dynamics of two atoms interacting with a vacuum multi-mode noise field. We show that the complete internal-state disentanglement of the two atoms, caused due to the atomic spontaneous emission can be achieved in a finite time.
基金Supported by the National Natural Science Foundation of China(61210007).
文摘Learning disentangled representation of data is a key problem in deep learning.Specifically,disentangling 2D facial landmarks into different factors(e.g.,identity and expression)is widely used in the applications of face reconstruction,face reenactment and talking head et al..However,due to the sparsity of landmarks and the lack of accurate labels for the factors,it is hard to learn the disentangled representation of landmarks.To address these problem,we propose a simple and effective model named FLD-VAE to disentangle arbitrary facial landmarks into identity and expression latent representations,which is based on a Variational Autoencoder framework.Besides,we propose three invariant loss functions in both latent and data levels to constrain the invariance of representations during training stage.Moreover,we implement an identity preservation loss to further enhance the representation ability of identity factor.To the best of our knowledge,this is the first work to end-to-end disentangle identity and expression factors simultaneously from one single facial landmark.
基金supported by National Natural Science Foundation of China under Grant Nos.60578014 and 10775023
文摘The disentanglement evolution of bipartite spin-1/2 system coupled to a common surrounding XY chain in transverse fields at nonzero temperature is studied in this letter. The dynamical process of the entanglement is numerically and analytically investigated. We find that thermal effects can enhance disentanglement if the entangled initial state of the central spins does not in the decoherence free space. The critical phenomenon of quantum phase transitions reflected in the disentanglement can be washed out by the thermal effect eventually.
基金supported by National Natural Science Foundation of China under Grant Nos. 60678022 and 10704001the Specialized Research Fund for the Doctoral Program of Higher Education under Grant No. 20060357008+2 种基金Anhui Provincial Natural Science Foundation under Grant No. 070412060the Talent Foundation of Anhui UniversityAnhui Key Laboratory of Information Materials and Devices (Anhui University)
文摘We investigate the entanglement evolution of two qubits that are initially in Werner state under the classical phase noise. We discuss the influence of mixture degree on disentanglement. It is showed that the more mixed the state, the shorter is the time of disentanglement.
文摘A straightforward simple proof is given that dark energy is the natural conse-quence of a quantum disentanglement physical process. Thus while the ordinary energy density of the cosmos is equal to half that of Hardy’s quantum probability of Entanglement i.e. where , the density of cosmic dark energy is consequently one minus divided by two i.e. . This result is in full agreement with all the numerous previous theoretical predictions as well as being in remarkable agreement with the overwhelming majority of cosmic accurate measurements and observations.
文摘We analyze the spin coincidence experiment considered by Bell in the derivation of Bells theorem. We solve the equation of motion for the spin system with a spin Hamiltonian, Hz, where the magnetic field is only in the z-direction. For the specific case of the coincidence experiment where the two magnets have the same orientation the Hamiltonian Hz commutes with the total spin Iz, which thus emerges as a constant of the motion. Bells argument is then that an observation of spin up at one magnet A necessarily implies spin down at the other B. For an isolated spin system A-B with classical translational degrees of freedom and an initial spin singlet state there is no force on the spin particles A and B. The spins are fully entangled but none of the spin particles A or B are deflected by the Stern-Gerlach magnets. This result is not compatible with Bells assumption that spin 1/2 particles are deected in a Stern-Gerlach device. Assuming a more realistic Hamiltonian Hz + Hx including a gradient in x direction the total Iz is not conserved and fully entanglement is not expected in this case. The conclusion is that Bells theorem is not applicable to spin coincidence measurement originally discussed by Bell.
基金supported by the National Natural Science Foundation of China(Grant Nos.62141214 and 62272171).
文摘Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation. Disentangled GCNs have been proposed to divide each node’s representation into several feature units. However, current disentangling methods do not try to figure out how many inherent factors the model should assign to help extract the best representation of each node. This paper then proposes D^(2)-GCN to provide dynamic disentanglement in GCNs and present the most appropriate factorization of each node’s mixed features. The convergence of the proposed method is proved both theoretically and experimentally. Experiments on real-world datasets show that D^(2)-GCN outperforms the baseline models concerning node classification results in both single- and multi-label tasks.
基金supported in part by the National Key R&D Program of China(No.2022ZD0116500)in part by the National Natural Science Foundation of China(No.62206284)。
文摘In the field of brain decoding research,reconstructing visual perception from neural recordings is a challenging but crucial task.With the use of superior algorithms,many methods have been dedicated to enhancing decoding performance.However,these models that map neural activities onto semantically entangled feature space are difficult to interpret.It is hard to understand the connections between neural activities and these abstract features.In this paper,we propose an interpretable neural decoding model that projects neural activities onto a semantically disentangled feature space with each dimension representing distinct visual attributes,such as gender and facial pose.A two-stage algorithm is designed to achieve this goal.First,a deep generative model learns semantically-disentangled image representations in an unsupervised way.Second,neural activities are linearly embedded into the semantic space,which the generator uses to reconstruct visual stimuli.Due to modality heterogeneity,it is challenging to learn such a neural embedded high-level semantic representation.We induce pixel,feature,and semantic alignment to ensure reconstruction quality.Three experimental fMRI datasets containing handwritten digits,characters,and human face stimuli are used to evaluate the neural decoding performance of our model.We also demonstrate the model interpretability through a reconstructed image editing application.The experimental results indicate that our model maintains a competitive decoding performance while remaining interpretable.
基金supported by the NCCR MARVEL,a National Center of Competence in Research,funded by the Swiss National Science Foundation(grant number 205602)YJ acknowledge support by the China Scholarship Council program+5 种基金JQ acknowledges support by the HORIZON-RIA 2D-PRINTABLE(proposal number:101135196)this work has received funding from the Swiss State Secretariat for Education,Research and Innovation(SERI)NP and GP acknowledge support by the Swiss National Science Foundation(SNSF)Project Funding(grant 200021E_206190 FISH4DIET)WZ acknowledge support by the National Key Research and Development Program of China(Grant No.2022YFB4400200)National Natural Science Foundation of China(Grant Nos.T2394474,T2394470)the Beijing Outstanding Young Scientist Program and Tencent Foundation through the XPLORER PRIZE.We acknowledge access to Piz Daint or Alps at the Swiss National Supercomputing Center,Switzerland under MARVEL's share with the project ID mr32.We acknowledge fruitful discussions with Edward Baxter Linscott and Miki Bonacci.
文摘Maximally-localized Wannier functions(MLWFs)are widely employed as an essential tool for calculating the physical properties of materials due to their localized nature and computational efficiency.Projectability-disentangled Wannier functions(PDWFs)have recently emerged as a reliable and efficient approach for automatically constructing MLWFs that span both occupied and lowest unoccupied bands.Here,we extend the applicability of PDWFs to magnetic systems and/or those including spin-orbit coupling,and implement such extensions in automated workflows.Furthermore,we enhance the robustness and reliability of constructing PDWFs by defining an extended protocol that automatically expands the projectors manifold,when required,by introducing additional appropriate hydrogenic atomic orbitals.We benchmark our extended protocol on a set of 200 chemically diverse materials,as well as on the 40 systems with the largest band distance obtained with the standard PDWF approach,showing that on our test set the present approach delivers a success rate of over 98%in obtaining accurate Wannier-function interpolations,defined as an average band distance below20 meV between the DFT and Wannier-interpolated bands,up to 2 eV above the Fermi level for metals or above the conduction band minimum for insulators(and a 100%success rate when including only bands up to 1 eV above these values).
基金sponsored in part by the National Key Research and Development Program of China(No.2023YFB3307500)the Science and Technology Innovation Project of Hunan Province(No.2023RC4014)the National Natural Science Foundation of China(NSFC)(Grant Nos.62076146,62021002,U20A6003,6212780016).
文摘1 Introduction Molecular Property Prediction aims to identify molecules sharing similar efficacious properties[1],which is a foundational task in drug discovery,materials science and bioinformatics.Graph neural networks(GNNs)have shown significant success in this field.However,GNN-based methods often face label scarcity,limiting their performance in predicting molecular properties.Besides,GNNs trained on specific datasets frequently struggle with generalization due to domain shift[2].
基金financially supported by the National Natural Science Foundation of China(Nos.22341303,22103079,and 22503003)the Shandong Provincial Natural Science Foundation(No.ZR2023QB232)the Beijing Institute of Technology Research Fund Program for Young Scholars(No.RCPT-6120250009)。
文摘Shear stress overshoot in entangled polymer rheology is a hallmark of transient dynamics,but its microscopic origin remains under debate.Using molecular dynamics simulations,we investigate a two-step shear protocol consisting of successive startup shears separated by a waiting period,with the first shear interrupted before the overshoot.In the homogeneous flow,the GLaMM theory captures the stress response during the first shear,but fails to reproduce the nonmonotonic dependence of the second stress overshoot(σ_(2max))on the waiting time.Contrary to the prediction of a nonmonotonic normal stress component σ_(yy)during the waiting period,our simulations show that σ_(yy),like the tube segment orientation(S_(xy)),the contour length of the primitive chain(L),and the entanglement number per chain(Z),relaxes monotonically toward equilibrium.At the strain corresponding to σ_(2max),both the tube segment orientation and the entanglement number per chain exhibit a nonmonotonic dependence on the waiting time that closely mirrors the behavior of σ_(2max),indicating that both factors play significant roles in governing(σ_(2max).Our findings are consistent with the interpretation of lanniruberto and Ma rrucci[ACS Macro.Lett.2014,3,552]for orientation effects and with the viewpoint of Wang et al.[Macromolecules 2013,46,3147]for entanglement effects,although the two explanations are rooted in distinct physical pictu res.These results provide new insights into the stress responses of entanglement polymer fluids and underscore the need for a more unified theoretical framework.
基金Edith Cowan University(ECU),Australia and Higher Education Commission(HEC)Pakistan,The Islamia University of Bahawalpur(IUB)Pakistan(5-1/HRD/UE STPI(Batch-V)/1182/2017/HEC).
文摘The capability of Convolutional Neural Networks(CNNs)for sparse representation has significant application to complex tasks like Representation Learning(RL).However,labelled datasets of sufficient size for learning this representation are not easily obtainable.The unsupervised learning capability of Variational Autoencoders(VAEs)and Generative Adversarial Networks(GANs)provide a promising solution to this issue through their capacity to learn representations for novel data samples and classification tasks.In this research,a texture-based latent space disentanglement technique is proposed to enhance learning of representations for novel data samples.A comparison is performed among different VAEs and GANs with the proposed approach for synthesis of new data samples.Two different VAE architectures are considered,a single layer dense VAE and a convolution based VAE,to compare the effectiveness of different architectures for learning of the representations.The GANs are selected based on the distance metric for disjoint distribution divergence estimation of complex representation learning tasks.The proposed texture-based disentanglement has been shown to provide a significant improvement for disentangling the process of representation learning by conditioning the random noise and synthesising texture rich images of fruit and vegetables。
基金supported by the National Natural Science Foundation of China (41701299)support from the Academy of Finland funding PARKTRAITS project (WBS 1315987)
文摘A complete ecosystem is also a complex network in which multifarious species interact with each other to achieve system-level functions, such as nutrient biogeochemistry (1)Microbial community is commonly considered as the primary driving force of ecosystem nutrient mobilization and metabolism, especially carbon (C), nitrogen (N), phosphorus (P), sulfur (S) and methane coupling process (2)The rise of metagenomics and high-throughput array (e.g. PhyloChip, GeoChip, etc.
文摘The dynamics of the center-of-mass of entangled polymer is assumed to be of 1-dimen-sional Brownian motion in a constrained tube. When the length fluctuation of the constrain-ed tube is neglected, the asymptotic relation between the relaxation time for disentangle-ment τ and the chain length N is obtained, i.e. τ～N^3. Under conditions of the finite chainlength and the length fluctuation of an effective constrained tube, the dependence relation τ～N^(3.40±0.16) is obtained by computer simulation. This conclusion elucidates reasonably the knownexperimental results about the dynamics of real entangled polymers.
基金supported by the National Natural Science Foundation of China(No.U19A2059)the 2022 Research Foundation of Chengdu Textile College(No.X22032161).
文摘Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict relations.However,subgraphs may contain disconnected regions,which usually represent different semantic ranges.Because not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic aggregation.To indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are updated.The disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph structures.Furthermore,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the subgraphs.Experimentally,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@10.Experiments prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.
基金supported by the National Natural Science Foundation of China(Nos.61825103,62202349)the Natural Science Foundation of Hubei Province(Nos.2022CFB352,2020CFA001)the Key Research&Development of Hubei Province(No.2020BIB006).
文摘representation that can identify and isolate different potential variables hidden in the highdimensional observations.Disentangled representation learning can capture information about a single change factor and control it by the corresponding potential subspace,providing a robust representation for complex changes in the data.In this paper,we first introduce and analyze the current status of research on disentangled representation and its causal mechanisms and summarize three crucial properties of disentangled representation.Then,disentangled representation learning algorithms are classified into four categories and outlined in terms of both mathematical description and applicability.Subsequently,the loss functions and objective evaluation metrics commonly used in existing work on disentangled representation are classified.Finally,the paper summarizes representative applications of disentangled representation learning in the field of remote sensing and discusses its future development.
文摘In recent years,the concept of digital human has attracted widespread attention from all walks of life,and the modelling of high-fidelity human bodies,heads,and hands has been intensively studied.This paper focuses on head modelling and proposes a generic head parametric model based on neural radiance fields.Specifically,we first use face recognition networks and 3D facial expression database FaceWarehouse to parameterize identity and expression semantics,respectively,and use both as conditional inputs to build a neural radiance field for the human head,thereby improving the head model’s representation ability while ensuring editing capabilities for the identity and expression of the rendered results;then,through a combination of volume rendering and neural rendering,the 3D representation of the head is rapidly rendered into the 2D plane,producing a high-fidelity image of the human head.Thanks to the well-designed loss functions and good implicit representation of the neural radiance field,our model can not only edit the identity and expression independently,but also freely modify the virtual camera position of the rendering results.It has excellent multi-view consistency,and has many applications in novel view synthesis,pose driving and more.
