M
Meng Wang
Researcher at Southeast University
Publications - 167
Citations - 5744
Meng Wang is an academic researcher from Southeast University. The author has contributed to research in topics: Graph (abstract data type) & Computer science. The author has an hindex of 22, co-authored 153 publications receiving 2108 citations. Previous affiliations of Meng Wang include Yanshan University & Hefei University of Technology.
Papers
More filters
Posted Content
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
TL;DR: This work proposes a new model named LightGCN, including only the most essential component in GCN -- neighborhood aggregation -- for collaborative filtering, and is much easier to implement and train, exhibiting substantial improvements over Neural Graph Collaborative Filtering (NGCF) under exactly the same experimental setting.
Proceedings ArticleDOI
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
TL;DR: LightGCN as mentioned in this paper learns user and item embedding by linearly propagating them on the user-item interaction graph, and uses the weighted sum of the embeddings learned at all layers as the final embedding.
Proceedings ArticleDOI
A Neural Influence Diffusion Model for Social Recommendation
TL;DR: Zhang et al. as discussed by the authors proposed a deep influence propagation model to stimulate how users are influenced by the recursive social diffusion process for social recommendation, which can be applied when the user~(item) attributes or the social network structure is not available.
Journal ArticleDOI
Revisiting Graph Based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
TL;DR: LR-GCCF as mentioned in this paper revisited GCN based CF models from two aspects, and empirically showed that removing non-linearities would enhance recommendation performance, which is consistent with the theories in simple graph convolutional networks.
Journal ArticleDOI
Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
TL;DR: This paper proposes a novel unsupervised video hashing framework dubbed SSVH, which is able to capture the temporal nature of videos in an end-to-end learning to hash fashion, and designs a hierarchical binary auto-encoder to model the temporal dependencies in videos with multiple granularities.