142 citations · 514 across the 32 of their papers we have counts for
8 papers · 1 filter
Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
Eli Chien, Wei-Ning Chen, Chao Pan +3
GNNs can inadvertently expose sensitive user information and interactions through their model predictions. To address these privacy concerns, Differential Privacy (DP) protocols ar…
Polynomial Width is Sufficient for Set Representation with High-dimensional Features
Peihao Wang, Shenghao Yang, Shu Li +2
Set representation has become ubiquitous in deep learning for modeling the inductive bias of neural networks that are insensitive to the input order. DeepSets is the most widely us…
Structural Re-weighting Improves Graph Domain Adaptation
Shikun Liu, Tianchun Li, Yongbin Feng +4
In many real-world applications, graph-structured data used for training and testing have differences in distribution, such as in high energy physics (HEP) where simulation data us…
Hierarchical Reinforcement Learning for Modeling User Novelty-Seeking Intent in Recommender Systems
Pan Li, Yuyan Wang, Ed H. Chi +1
Recommending novel content, which expands user horizons by introducing them to new interests, has been shown to improve users' long-term experience on recommendation platforms \cit…
Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations
Pan Li, Yuyan Wang, Ed H. Chi +1
Existing aspect extraction methods mostly rely on explicit or ground truth aspect information, or using data mining or machine learning approaches to extract aspects from implicit…
Less is More: Revisiting the Gaussian Mechanism for Differential Privacy
Tianxi Ji, Pan Li
Differential privacy via output perturbation has been a de facto standard for releasing query or computation results on sensitive data. However, we identify that all existing Gauss…