Sequential recommendation based on amulti-interest framework aims to analyze different aspects of interest based on historical interactions and generate predictions of a user’s potential interest in a list of items.M...Sequential recommendation based on amulti-interest framework aims to analyze different aspects of interest based on historical interactions and generate predictions of a user’s potential interest in a list of items.Most existing methods only focus on what are themultiple interests behind interactions but neglect the evolution of user interests over time.To explore the impact of temporal dynamics on interest extraction,this paper explicitly models the timestamp with amulti-interest network and proposes a time-highlighted network to learn user preferences,which considers not only the interests at different moments but also the possible trends of interest over time.More specifically,the time intervals between historical interactions and prediction moments are first mapped to vectors.Meanwhile,a time-attentive aggregation layer is designed to capture the trends of items in the sequence over time,where the time intervals are seen as additional information to distinguish the importance of different neighbors.Then,the learned items’transition trends are aggregated with the items themselves by a gated unit.Finally,a self-attention network is deployed to capture multiple interests with the obtained temporal information vectors.Extensive experiments are carried out based on three real-world datasets and the results convincingly establish the superiority of the proposed method over other state-of-the-art baselines in terms of model performance.展开更多
Effective news recommendation is crucial for alleviating users’information overload.While recent prompt-based news recommendation methods have shown promising performance by reformulating the recommendation task as a...Effective news recommendation is crucial for alleviating users’information overload.While recent prompt-based news recommendation methods have shown promising performance by reformulating the recommendation task as a masked prediction problem,we note that this paradigm still faces several major limitations including inadequate multi-interest representation,limited global interaction modeling,and historical interaction truncation.To address these problems,this paper proposes PCRec,a prompt-guided cross-view contrastive learning framework for multi-interest news recommendation.PCRec first introduces feature-level prompts to overcome the input constraints inherent in text-level prompts.Moreover,a two-stage user modeling module is designed to capture users’multi-interests.Finally,to model global user-news relationships,PCRec implements a cross-view contrastive learning strategy.This approach groups similar users,enabling learning from multiple perspectives and breaking down isolated relationships among users,news categories,and news subcategories.Extensive experiments on two real-world news recommendation datasets validate the superiority of our proposed PCRec compared with various state-of-the-art baselines.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 61702060.
文摘Sequential recommendation based on amulti-interest framework aims to analyze different aspects of interest based on historical interactions and generate predictions of a user’s potential interest in a list of items.Most existing methods only focus on what are themultiple interests behind interactions but neglect the evolution of user interests over time.To explore the impact of temporal dynamics on interest extraction,this paper explicitly models the timestamp with amulti-interest network and proposes a time-highlighted network to learn user preferences,which considers not only the interests at different moments but also the possible trends of interest over time.More specifically,the time intervals between historical interactions and prediction moments are first mapped to vectors.Meanwhile,a time-attentive aggregation layer is designed to capture the trends of items in the sequence over time,where the time intervals are seen as additional information to distinguish the importance of different neighbors.Then,the learned items’transition trends are aggregated with the items themselves by a gated unit.Finally,a self-attention network is deployed to capture multiple interests with the obtained temporal information vectors.Extensive experiments are carried out based on three real-world datasets and the results convincingly establish the superiority of the proposed method over other state-of-the-art baselines in terms of model performance.
基金supported by the National Key Research and Development Program of China under Grant No.2024YFF0729003the National Natural Science Foundation of China under Grant Nos.62176014 and 62276015the Fundamental Research Funds for the Central Universities of China.
文摘Effective news recommendation is crucial for alleviating users’information overload.While recent prompt-based news recommendation methods have shown promising performance by reformulating the recommendation task as a masked prediction problem,we note that this paradigm still faces several major limitations including inadequate multi-interest representation,limited global interaction modeling,and historical interaction truncation.To address these problems,this paper proposes PCRec,a prompt-guided cross-view contrastive learning framework for multi-interest news recommendation.PCRec first introduces feature-level prompts to overcome the input constraints inherent in text-level prompts.Moreover,a two-stage user modeling module is designed to capture users’multi-interests.Finally,to model global user-news relationships,PCRec implements a cross-view contrastive learning strategy.This approach groups similar users,enabling learning from multiple perspectives and breaking down isolated relationships among users,news categories,and news subcategories.Extensive experiments on two real-world news recommendation datasets validate the superiority of our proposed PCRec compared with various state-of-the-art baselines.
