87 citations · 254 across the 10 of their papers we have counts for
4 papers · 1 filter
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Chulin Xie, Minghao Chen, Pin-Yu Chen +1
Federated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However,…
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
Hao-Zhe Feng, Kezhi Kong, Minghao Chen +3
Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference r…
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
Hao-Zhe Feng, Zhaoyang You, Minghao Chen +5
Conventional unsupervised multi-source domain adaptation (UMDA) methods assume all source domains can be accessed directly. This neglects the privacy-preserving policy, that is, al…
Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation
Jia Guo, Minghao Chen, Yao Hu +3
Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the stud…