activity
20242026
collaborators

5 papers

cs.LG2026

Optimal Look-back Horizon for Time Series Forecasting in Federated Learning

Dahao Tang, Nan Yang, Yanli Li +3

Selecting an appropriate look-back horizon remains a fundamental challenge in time series forecasting (TSF), particularly in the federated learning scenarios where data is decentra…

cs.LG2025

PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN

Jiayu Zhang, Zhiyu Zhu, Xinyi Wang +4

Deep neural networks have demonstrated remarkable performance across various domains. However, they are vulnerable to adversarial examples, which can lead to erroneous predictions.…

cs.LG2025

ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability

Zhiyu Zhu, Jiayu Zhang, Zhibo Jin +2

Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing fr…

cs.CV2025

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Zhiyu Zhu, Zhibo Jin, Jiayu Zhang +4

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), whi…

cs.AI2024

Attribution for Enhanced Explanation with Transferable Adversarial eXploration

Zhiyu Zhu, Jiayu Zhang, Zhibo Jin +3

The interpretability of deep neural networks is crucial for understanding model decisions in various applications, including computer vision. AttEXplore++, an advanced framework bu…