activity
20182024
most citedUnifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences

647 citations · 1.7k across the 12 of their papers we have counts for

collaborators
Showing cs.IRShow all

12 papers · 1 filter

cs.IR2021

GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

Wei Yinwei, Wang Xiang, Nie Liqiang +2

Reorganizing implicit feedback of users as a user-item interaction graph facilitates the applications of graph convolutional networks (GCNs) in recommendation tasks. In the interac…

cs.IR20211 cited

Hierarchical User Intent Graph Network forMultimedia Recommendation

Wei Yinwei, Wang Xiang, He Xiangnan +3

In this work, we aim to learn multi-level user intents from the co-interacted patterns of items, so as to obtain high-quality representations of users and items and further enhance…

cs.IR202113 cited

Contrastive Learning for Cold-Start Recommendation

Yinwei Wei, Xiang Wang, Qi Li +4

Recommending cold-start items is a long-standing and fundamental challenge in recommender systems. Without any historical interaction on cold-start items, CF scheme fails to use co…

cs.IR2021164 cited

Deconfounded Recommendation for Alleviating Bias Amplification

Wenjie Wang, Fuli Feng, Xiangnan He +2

Recommender systems usually amplify the biases in the data. The model learned from historical interactions with imbalanced item distribution will amplify the imbalance by over-reco…

cs.IR2021579 cited

Learning Intents behind Interactions with Knowledge Graph for Recommendation

Xiang Wang, Tinglin Huang, Dingxian Wang +4

Knowledge graph (KG) plays an increasingly important role in recommender systems. A recent technical trend is to develop end-to-end models founded on graph neural networks (GNNs).…

cs.IR2020161 cited

Interactive Path Reasoning on Graph for Conversational Recommendation

Wenqiang Lei, Gangyi Zhang, Xiangnan He +4

Traditional recommendation systems estimate user preference on items from past interaction history, thus suffering from the limitations of obtaining fine-grained and dynamic user p…