← Search

Likun Zhang

2 accepted papers

2024

Interpreting Memorization in Deep Learning from Data Distribution

ICASSP 2024accepted

A deep learning model can be vulnerable to a membership inference attack (MIA) which allows an attacker to determine if a specific data record was used for its training. In this paper, we investigate the unfairness of disparate vulnerability to MIA across different subgroups in terms of their data d…

Cited by 0SourceScholar
2023

An Ensemble Distillation Framework for Sentence Embeddings with Multilingual Round-Trip Translation

AAAI 2023technical

In this work, we propose a novel unsupervised contrastive learning framework to improve state-of-the-art sentence embeddings. First, we train a set of contrastive submodels which take multilingual round-trip translation(RTT) as data augmentation. The RTT naturally changes the length of the same sent…