Hongyang Zhang

Noise-Tolerant Interactive Learning from Pairwise Comparisons

2017 · arXiv (Cornell University)

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. …

A Law of Robustness beyond Isoperimetry

2022 · arXiv (Cornell University)

We study the robust interpolation problem of arbitrary data distributions supported on a bounded space and propose a two-fold law of robustness. Robust interpolation refers to the problem of interpolating $n$ noisy training data points …

Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets

2023 · arXiv (Cornell University)

Despite incredible advances, deep learning has been shown to be susceptible to adversarial attacks. Numerous approaches have been proposed to train robust networks both empirically and certifiably. However, most of them defend against only a …

Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models

2023 · arXiv (Cornell University)

In this paper, we study the problem of generating obstinate (over-stability) adversarial examples by word substitution in NLP, where input text is meaningfully changed but the model's prediction does not, even though it should. Previous …

Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking

2022

In information retrieval (IR), candidate set pruning has been commonly used to speed up two-stage relevance ranking. However, such an approach lacks accurate error control and often trades accuracy against computational efficiency in an empirical …

Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification

2024 · arXiv (Cornell University)

Generalizable vehicle re-identification (ReID) seeks to develop models that can adapt to unknown target domains without the need for additional fine-tuning or retraining. Previous works have mainly focused on extracting domain-invariant features by aligning data …