activity
20162023
most citedLearning Fair Node Representations with Graph Counterfactual Fairness

77 citations · 429 across the 30 of their papers we have counts for

collaborators
Showing 2022Show all

11 papers · 1 filter

cs.SI2022★ 1 cited

Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Ujun Jeong, Kaize Ding, Lu Cheng +3

Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society. Assessing the authenticity of news is challenging due to…

cs.LG2022

Distributional Shift Adaptation using Domain-Specific Features

Anique Tahir, Lu Cheng, Ruocheng Guo +1

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming…

cs.LG2022★ 18 cited

CLEAR: Generative Counterfactual Explanations on Graphs

Jing Ma, Ruocheng Guo, Saumitra Mishra +2

Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted lab…

cs.IR2022★ 1 cited

Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective

Weijieying Ren, Lei Wang, Kunpeng Liu +3

Recommender systems learn from historical user-item interactions to identify preferred items for target users. These observed interactions are usually unbalanced following a long-t…

cs.IR2022★ 2 cited

MLP4Rec: A Pure MLP Architecture for Sequential Recommendations

Muyang Li, Xiangyu Zhao, Chuan Lyu +3

Self-attention models have achieved state-of-the-art performance in sequential recommender systems by capturing the sequential dependencies among user-item interactions. However, t…

cs.IR2022★ 1 cited

Causal Disentanglement with Network Information for Debiased Recommendations

Paras Sheth, Ruocheng Guo, Lu Cheng +2

Recommender systems aim to recommend new items to users by learning user and item representations. In practice, these representations are highly entangled as they consist of inform…