35 citations · 224 across the 26 of their papers we have counts for
16 papers · 1 filter
Personalized Federated Learning with Feature Alignment and Classifier Collaboration
Jian Xu, Xinyi Tong, Shao-Lun Huang
Data heterogeneity is one of the most challenging issues in federated learning, which motivates a variety of approaches to learn personalized models for participating clients. One…
An Information-Theoretic Approach to Transferability in Task Transfer Learning
Yajie Bao, Yang Li, Shao-Lun Huang +4
Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question i…
Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge
Jingge Wang, Liyan Xie, Yao Xie +2
Domain generalization aims at learning a universal model that performs well on unseen target domains, incorporating knowledge from multiple source domains. In this research, we con…
Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithms
Runpeng Yu, Hong Zhu, Kaican Li +5
Due to the poor generalization performance of traditional empirical risk minimization (ERM) in the case of distributional shift, Out-of-Distribution (OoD) generalization algorithms…
PAC-Bayes Information Bottleneck
Zifeng Wang, Shao-Lun Huang, Ercan E. Kuruoglu +3
Understanding the source of the superior generalization ability of NNs remains one of the most important problems in ML research. There have been a series of theoretical works tryi…
Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering
Jian Xu, Shao-Lun Huang, Linqi Song +1
Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either…
Maximum Likelihood Estimation for Multimodal Learning with Missing Modality
Fei Ma, Xiangxiang Xu, Shao-Lun Huang +1
Multimodal learning has achieved great successes in many scenarios. Compared with unimodal learning, it can effectively combine the information from different modalities to improve…
DQ-SGD: Dynamic Quantization in SGD for Communication-Efficient Distributed Learning
Guangfeng Yan, Shao-Lun Huang, Tian Lan +1
Gradient quantization is an emerging technique in reducing communication costs in distributed learning. Existing gradient quantization algorithms often rely on engineering heuristi…
OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations
Yang Tan, Yang Li, Shao-Lun Huang
Transfer learning across heterogeneous data distributions (a.k.a. domains) and distinct tasks is a more general and challenging problem than conventional transfer learning, where e…
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
Zifeng Wang, Xi Chen, Rui Wen +3
Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommen…
Finding Influential Instances for Distantly Supervised Relation Extraction
Zifeng Wang, Rui Wen, Xi Chen +3
Distant supervision (DS) is a strong way to expand the datasets for enhancing relation extraction (RE) models but often suffers from high label noise. Current works based on attent…
Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
Zifeng Wang, Rui Wen, Xi Chen +4
We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users based on Electronic Healthcare Records (EHRs). Two main chall…
On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
Zifeng Wang, Xi Chen, Rui Wen +1
Observed events in recommendation are consequence of the decisions made by a policy, thus they are usually selectively labeled, namely the data are Missing Not At Random (MNAR), wh…
Less Is Better: Unweighted Data Subsampling via Influence Function
Zifeng Wang, Hong Zhu, Zhenhua Dong +2
In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling.…
On Universal Features for High-Dimensional Learning and Inference
Shao-Lun Huang, Anuran Makur, Gregory W. Wornell +1
We consider the problem of identifying universal low-dimensional features from high-dimensional data for inference tasks in settings involving learning. For such problems, we intro…
An Efficient Approach to Informative Feature Extraction from Multimodal Data
Lichen Wang, Jiaxiang Wu, Shao-Lun Huang +4
One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the…