← Search

Weichao Zhang

2 accepted papers

2026

Subspace-Aware Feature Reshaping for Open-Set Graph Class-Incremental Learning

ICML 2026poster

Graph class-incremental learning (GCIL) has emerged to address the challenge of learning from dynamically evolving graphs, which continuously learns new classes over a sequence of tasks while retaining performance on previously seen classes. However, existing GCIL methods assume a closed-set test di…

Cited by 0SourceScholar
2024

Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method

EMNLP 2024main

As the scale of training corpora for large language models (LLMs) grows, model developers become increasingly reluctant to disclose details on their data. This lack of transparency poses challenges to scientific evaluation and ethical deployment. Recently, pretraining data detection approaches, whic…