5 papers
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
Quang Duc Nguyen, Siyuan Liang, Yiming Li +2
Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in t…
Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
Phuc Duc Nguyen, Quang Duc Nguyen
Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Existing class-wise targeted attac…
WAVE++: Capturing Within-Task Variance for Continual Relation Extraction with Adaptive Prompting
Bao-Ngoc Dao, Minh Le, Quang Nguyen +3
Memory-based approaches have shown strong performance in Continual Relation Extraction (CRE). However, storing examples from previous tasks increases memory usage and raises privac…
LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection
Bao-Ngoc Dao, Quang Nguyen, Luyen Ngo Dinh +2
Few-shot Continual Event Detection (FCED) poses the dual challenges of learning from limited data and mitigating catastrophic forgetting across sequential tasks. Existing approache…
GloCOM: A Short Text Neural Topic Model via Global Clustering Context
Quang Duc Nguyen, Tung Nguyen, Duc Anh Nguyen +3
Uncovering hidden topics from short texts is challenging for traditional and neural models due to data sparsity, which limits word co-occurrence patterns, and label sparsity, stemm…