Recent years have witnessed the great success of self-supervised learning(SSL)in recommendation systems.However,SSL recommender models are likely to suffer from spurious correlations,leading to poor generalization.To ...Recent years have witnessed the great success of self-supervised learning(SSL)in recommendation systems.However,SSL recommender models are likely to suffer from spurious correlations,leading to poor generalization.To mitigate spurious correlations,existing work usually pursues ID-based SSL recommendation or utilizes feature engineering to identify spurious features.Nevertheless,ID-based SSL approaches sacrifice the positive impact of invariant features,while feature engineering methods require high-cost human labeling.To address the problems,we aim to automatically mitigate the effect of spurious correlations.This objective requires to 1)automatically mask spurious features without supervision,and 2)block the negative effect transmission from spurious features to other features during SSL.To handle the two challenges,we propose an invariant feature learning framework,which first divides user-item interactions into multiple environments with distribution shifts and then learns a feature mask mechanism to capture invariant features across environments.Based on the mask mechanism,we can remove the spurious features for robust predictions and block the negative effect transmission via mask-guided feature augmentation.Extensive experiments on two datasets demonstrate the effectiveness of the proposed framework in mitigating spurious correlations and improving the generalization abilities of SSL models.展开更多
Deep learning relies on learning from extensive data to generate prediction results.This approach may inadvertently capture spurious correlations within the data,leading to models that lack interpretability and robust...Deep learning relies on learning from extensive data to generate prediction results.This approach may inadvertently capture spurious correlations within the data,leading to models that lack interpretability and robustness.Researchers have developed more profound and stable causal inference methods based on cognitive neuroscience.By replacing the correlation model with a stable and interpretable causal model,it is possible to mitigate the misleading nature of spurious correlations and overcome the limitations of model calculations.In this survey,we provide a comprehensive and structured review of causal inference methods in deep learning.Brain-like inference ideas are discussed from a brain-inspired perspective,and the basic concepts of causal learning are introduced.The article describes the integration of causal inference with traditional deep learning algorithms and illustrates its application to large model tasks as well as specific modalities in deep learning.The current limitations of causal inference and future research directions are discussed.Moreover,the commonly used benchmark datasets and the corresponding download links are summarized.展开更多
文摘Recent years have witnessed the great success of self-supervised learning(SSL)in recommendation systems.However,SSL recommender models are likely to suffer from spurious correlations,leading to poor generalization.To mitigate spurious correlations,existing work usually pursues ID-based SSL recommendation or utilizes feature engineering to identify spurious features.Nevertheless,ID-based SSL approaches sacrifice the positive impact of invariant features,while feature engineering methods require high-cost human labeling.To address the problems,we aim to automatically mitigate the effect of spurious correlations.This objective requires to 1)automatically mask spurious features without supervision,and 2)block the negative effect transmission from spurious features to other features during SSL.To handle the two challenges,we propose an invariant feature learning framework,which first divides user-item interactions into multiple environments with distribution shifts and then learns a feature mask mechanism to capture invariant features across environments.Based on the mask mechanism,we can remove the spurious features for robust predictions and block the negative effect transmission via mask-guided feature augmentation.Extensive experiments on two datasets demonstrate the effectiveness of the proposed framework in mitigating spurious correlations and improving the generalization abilities of SSL models.
基金supported in part by the Key Scientific Technological Innovation Research Project of the Ministry of Education,the Joint Funds of the National Natural Science Foundation of China(U22B2054)the National Natural Science Foundation of China(62076192,61902298,61573267,61906150,and 62276199)+2 种基金the 111 Project,the Program for Cheung Kong Scholars and Innovative Research Team in University(IRT 15R53)the Science and Technology Innovation Project from the Chinese Ministry of Education,the Key Research and Development Program in Shaanxi Province of China(2019ZDLGY03-06)the China Postdoctoral Fund(2022T150506).
文摘Deep learning relies on learning from extensive data to generate prediction results.This approach may inadvertently capture spurious correlations within the data,leading to models that lack interpretability and robustness.Researchers have developed more profound and stable causal inference methods based on cognitive neuroscience.By replacing the correlation model with a stable and interpretable causal model,it is possible to mitigate the misleading nature of spurious correlations and overcome the limitations of model calculations.In this survey,we provide a comprehensive and structured review of causal inference methods in deep learning.Brain-like inference ideas are discussed from a brain-inspired perspective,and the basic concepts of causal learning are introduced.The article describes the integration of causal inference with traditional deep learning algorithms and illustrates its application to large model tasks as well as specific modalities in deep learning.The current limitations of causal inference and future research directions are discussed.Moreover,the commonly used benchmark datasets and the corresponding download links are summarized.
