110 citations · 336 across the 32 of their papers we have counts for
6 papers · 1 filter
FairBatch: Batch Selection for Model Fairness
Yuji Roh, Kangwook Lee, Steven Euijong Whang +1
Training a fair machine learning model is essential to prevent demographic disparity. Existing techniques for improving model fairness require broad changes in either data preproce…
SLM: Learning a Discourse Language Representation with Sentence Unshuffling
Haejun Lee, Drew A. Hudson, Kangwook Lee +1
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training…
Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
Saurabh Agarwal, Hongyi Wang, Kangwook Lee +2
Distributed model training suffers from communication bottlenecks due to frequent model updates transmitted across compute nodes. To alleviate these bottlenecks, practitioners use…
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
Hongyi Wang, Kartik Sreenivasan, Shashank Rajput +5
Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training. The goal of a backdoor is to corrupt the perf…
Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
Changhun Jo, Kangwook Lee
Incorporating graph side information into recommender systems has been widely used to better predict ratings, but relatively few works have focused on theoretical guarantees. Ahn e…
FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
Yuji Roh, Kangwook Lee, Steven Euijong Whang +1
Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of d…