Fuli Feng
National University of Singapore
168 Papers
259 Citations
Fuli Feng is an academic researcher from National University of Singapore. The author has contributed to research in topics: Computer science & Recommender system. The author has an hindex of 23, co-authored 92 publications. Previous affiliations of Fuli Feng include Association for Computing Machinery & Beihang University.
Chat about Author
Papers
Invariant Representation Learning for Multimedia Recommendation
Xiaoyu Du,Zike Wu,Fuli Feng,Xiangnan He,Jinhui Tang +4 more
- 10 Oct 2022
TL;DR: Wang et al. as mentioned in this paper proposed an invariant representation learning framework (InvRL) to alleviate the impact of spurious correlations in the context of fashion recommendation, which utilizes environments to reflect the spurious correlations and determine each environment with a set of interactions.
33
•Posted Content
Learning Robust Recommenders through Cross-Model Agreement.
TL;DR: In this article, the authors proposed a cross-model agreement (DeCA) method to minimize the KL-divergence between the real user preference distributions parameterized by two recommendation models while maximizing the likelihood of data observation.
32
•Posted Content
Causal Incremental Graph Convolution for Recommender System Retraining.
TL;DR: In this paper, a causal incremental graph convolution (IGC) is proposed to fuse the long-term and short-term preference signals for recommender models. But the authors do not consider the effect of new data on the representation of inactive nodes.
30
Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
Fuli Feng,Weiran Huang,Xiangnan He,Xin Xin,Qifan Wang,Tat-Seng Chua +5 more
- 11 Jul 2021
TL;DR: In this article, the authors investigate whether a GCN should trust the local structure of a testing node when predicting its label, i.e., the labels of a node's neighbors could vary.
29
A Multi-facet Paradigm to Bridge Large Language Model and Recommendation
Xinyu Lin,Wenjie Wang,Yongqi Li,Fuli Feng,See-Kiong Ng,Tat-Seng Chua +5 more
TL;DR: This work proposes a novel multi-facet paradigm, namely TransRec, to bridge the LLMs to recommendation, and introduces a specialized data structure for TransRec to guarantee the in-corpus identifier generation and adopt substring indexing to encourage LLM to generate from any position.