Publications

This is our catalog of recent publications authored by IBM researchers, in collaboration with the global research community. We’re currently adding our back catalog of more than 110,000 publications. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.

Featured collections

Popular topics

Year

182 results for Pin-Yu Chen

How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
- - Shuai Zhang
  - Meng Weng
  - et al.
- 2022
- ICLR 2022
MAML is a Noisy Contrastive Learner in Classification
- - Chia-Hsiang Kao
  - Wei-Chen Chiu
  - et al.
- 2022
- ICLR 2022
Auto-Transfer: Learning to Route Transferable Representations
- - Keerthiram Murugesan
  - Vijay Sadashivaiah
  - et al.
- 2022
- ICLR 2022
AI Explainability 360: Impact and Design
- - Vijay Arya
  - Rachel Bellamy
  - et al.
- 2022
- IAAI 2022
Adversarial Attack Generation Empowered by Min-Max Optimization
- - Jingkang Wang
  - Tianyun Zhang
  - et al.
- 2021
- NeurIPS 2021
Catastrophic Data Leakage in Vertical Federated Learning
- - Xiao Jin
  - Pin-Yu Chen
  - et al.
- 2021
- NeurIPS 2021
Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations
- - Yu-Lin Tsai
  - Chia-Yi Hsu
  - et al.
- 2021
- NeurIPS 2021
Predicting Deep Neural Network Generalization with Perturbation Response Curves
- - Yair Schiff
  - Brian Quanz
  - et al.
- 2021
- NeurIPS 2021
Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
- - Akshay Mehra
  - Bhavya Kailkhura
  - et al.
- 2021
- NeurIPS 2021
Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks
- - Shuai Zhang
  - Meng Weng
  - et al.
- 2021
- NeurIPS 2021