Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Pin-Yu Chen

Pin-Yu Chen

Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics


Jan 14, 2022
Chunheng Jiang, Tejaswini Pedapati, Pin-Yu Chen, Yizhou Sun, Jianxi Gao

Figure 1 for Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics
Figure 2 for Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics
Figure 3 for Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics
Figure 4 for Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics
* 19 pages, 7 figures, neural architecture search, mean-field 
  Access Paper or Ask Questions

Network Graph Based Neural Architecture Search


Dec 15, 2021
Zhenhan Huang, Chunheng Jiang, Pin-Yu Chen, Jianxi Gao

Figure 1 for Network Graph Based Neural Architecture Search
Figure 2 for Network Graph Based Neural Architecture Search
Figure 3 for Network Graph Based Neural Architecture Search
Figure 4 for Network Graph Based Neural Architecture Search
* 12 pages 
  Access Paper or Ask Questions

Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework


Dec 08, 2021
Ching-Yun Ko, Jeet Mohapatra, Sijia Liu, Pin-Yu Chen, Luca Daniel, Lily Weng

Figure 1 for Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
Figure 2 for Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
Figure 3 for Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
Figure 4 for Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
* The full version of SSLNeurIPS'21 contributed talk (NeurIPS 2021 Workshop: Self-Supervised Learning - Theory and Practice). Work in progress 
  Access Paper or Ask Questions

Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines


Dec 01, 2021
Jiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, Z. Morley Mao

Figure 1 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Figure 2 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Figure 3 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Figure 4 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
* 21 pages, 15 figures, and 9 tables 
  Access Paper or Ask Questions

Pessimistic Model Selection for Offline Deep Reinforcement Learning


Nov 29, 2021
Chao-Han Huck Yang, Zhengling Qi, Yifan Cui, Pin-Yu Chen

Figure 1 for Pessimistic Model Selection for Offline Deep Reinforcement Learning
Figure 2 for Pessimistic Model Selection for Offline Deep Reinforcement Learning
Figure 3 for Pessimistic Model Selection for Offline Deep Reinforcement Learning
Figure 4 for Pessimistic Model Selection for Offline Deep Reinforcement Learning
* Preprint. A non-archival and preliminary venue was presented at NeurIPS 2021 Offline Reinforcement Learning Workshop 
  Access Paper or Ask Questions

Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis


Nov 28, 2021
Yu Hsuan Li, Tzu-Yin Chao, Ching-Chun Huang, Pin-Yu Chen, Wei-Chen Chiu

Figure 1 for Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Figure 2 for Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Figure 3 for Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Figure 4 for Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
* 18 pages, 14 figures 
  Access Paper or Ask Questions

Meta Adversarial Perturbations


Nov 19, 2021
Chia-Hung Yuan, Pin-Yu Chen, Chia-Mu Yu

Figure 1 for Meta Adversarial Perturbations
Figure 2 for Meta Adversarial Perturbations
Figure 3 for Meta Adversarial Perturbations

  Access Paper or Ask Questions

Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination


Nov 14, 2021
Arpan Mukherjee, Ali Tajer, Pin-Yu Chen, Payel Das

Figure 1 for Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination
Figure 2 for Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination
Figure 3 for Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination
Figure 4 for Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination

  Access Paper or Ask Questions

CAFE: Catastrophic Data Leakage in Vertical Federated Learning


Nov 02, 2021
Xiao Jin, Pin-Yu Chen, Chia-Yi Hsu, Chia-Mu Yu, Tianyi Chen

Figure 1 for CAFE: Catastrophic Data Leakage in Vertical Federated Learning
Figure 2 for CAFE: Catastrophic Data Leakage in Vertical Federated Learning
Figure 3 for CAFE: Catastrophic Data Leakage in Vertical Federated Learning
Figure 4 for CAFE: Catastrophic Data Leakage in Vertical Federated Learning

  Access Paper or Ask Questions

When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?


Nov 01, 2021
Lijie Fan, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Chuang Gan

Figure 1 for When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
Figure 2 for When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
Figure 3 for When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
Figure 4 for When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
* NeurIPS 2021. Code is available at https://github.com/LijieFan/AdvCL 
  Access Paper or Ask Questions

How and When Adversarial Robustness Transfers in Knowledge Distillation?


Oct 22, 2021
Rulin Shao, Jinfeng Yi, Pin-Yu Chen, Cho-Jui Hsieh

Figure 1 for How and When Adversarial Robustness Transfers in Knowledge Distillation?
Figure 2 for How and When Adversarial Robustness Transfers in Knowledge Distillation?
Figure 3 for How and When Adversarial Robustness Transfers in Knowledge Distillation?
Figure 4 for How and When Adversarial Robustness Transfers in Knowledge Distillation?

  Access Paper or Ask Questions

Robust Event Classification Using Imperfect Real-world PMU Data


Oct 19, 2021
Yunchuan Liu, Lei Yang, Amir Ghasemkhani, Hanif Livani, Virgilio A. Centeno, Pin-Yu Chen, Junshan Zhang

Figure 1 for Robust Event Classification Using Imperfect Real-world PMU Data
Figure 2 for Robust Event Classification Using Imperfect Real-world PMU Data
Figure 3 for Robust Event Classification Using Imperfect Real-world PMU Data
Figure 4 for Robust Event Classification Using Imperfect Real-world PMU Data

  Access Paper or Ask Questions

QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks


Oct 12, 2021
Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen

Figure 1 for QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
Figure 2 for QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
Figure 3 for QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
Figure 4 for QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks

  Access Paper or Ask Questions

Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks


Oct 12, 2021
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong

Figure 1 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
Figure 2 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
Figure 3 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
Figure 4 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
* Thirty-fifth Conference on Neural Information Processing Systems, 2021 
  Access Paper or Ask Questions

A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming


Oct 08, 2021
Hao Yen, Pin-Jui Ku, Chao-Han Huck Yang, Hu Hu, Sabato Marco Siniscalchi, Pin-Yu Chen, Yu Tsao

Figure 1 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
Figure 2 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
Figure 3 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
Figure 4 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

AI Explainability 360: Impact and Design


Sep 24, 2021
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang

Figure 1 for AI Explainability 360: Impact and Design
Figure 2 for AI Explainability 360: Impact and Design
Figure 3 for AI Explainability 360: Impact and Design
Figure 4 for AI Explainability 360: Impact and Design
* arXiv admin note: text overlap with arXiv:1909.03012 
  Access Paper or Ask Questions

Real-World Adversarial Examples involving Makeup Application


Sep 04, 2021
Chang-Sheng Lin, Chia-Yi Hsu, Pin-Yu Chen, Chia-Mu Yu

Figure 1 for Real-World Adversarial Examples involving Makeup Application
Figure 2 for Real-World Adversarial Examples involving Makeup Application
Figure 3 for Real-World Adversarial Examples involving Makeup Application
Figure 4 for Real-World Adversarial Examples involving Makeup Application

  Access Paper or Ask Questions

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning


Jul 08, 2021
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm

Figure 1 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Figure 2 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Figure 3 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Figure 4 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

  Access Paper or Ask Questions

MAML is a Noisy Contrastive Learner


Jun 29, 2021
Chia-Hsiang Kao, Wei-Chen Chiu, Pin-Yu Chen

Figure 1 for MAML is a Noisy Contrastive Learner
Figure 2 for MAML is a Noisy Contrastive Learner
Figure 3 for MAML is a Noisy Contrastive Learner
Figure 4 for MAML is a Noisy Contrastive Learner
* 15 pages, 11 figures 
  Access Paper or Ask Questions

Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design


Jun 24, 2021
Yue Cao, Payel Das, Vijil Chenthamarakshan, Pin-Yu Chen, Igor Melnyk, Yang Shen

Figure 1 for Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
Figure 2 for Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
Figure 3 for Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
Figure 4 for Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
* ICML 2021 
  Access Paper or Ask Questions

Voice2Series: Reprogramming Acoustic Models for Time Series Classification


Jun 17, 2021
Chao-Han Huck Yang, Yun-Yun Tsai, Pin-Yu Chen

Figure 1 for Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Figure 2 for Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Figure 3 for Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Figure 4 for Voice2Series: Reprogramming Acoustic Models for Time Series Classification
* Accepted to ICML 2021, 16 Pages 
  Access Paper or Ask Questions

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks


Jun 15, 2021
Chulin Xie, Minghao Chen, Pin-Yu Chen, Bo Li

Figure 1 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Figure 2 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Figure 3 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Figure 4 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
* ICML 2021 
  Access Paper or Ask Questions

Predicting Deep Neural Network Generalization with Perturbation Response Curves


Jun 09, 2021
Yair Schiff, Brian Quanz, Payel Das, Pin-Yu Chen

Figure 1 for Predicting Deep Neural Network Generalization with Perturbation Response Curves
Figure 2 for Predicting Deep Neural Network Generalization with Perturbation Response Curves
Figure 3 for Predicting Deep Neural Network Generalization with Perturbation Response Curves
Figure 4 for Predicting Deep Neural Network Generalization with Perturbation Response Curves
* arXiv admin note: substantial text overlap with arXiv:2104.03469 
  Access Paper or Ask Questions

Simple Transparent Adversarial Examples


May 20, 2021
Jaydeep Borkar, Pin-Yu Chen

Figure 1 for Simple Transparent Adversarial Examples
Figure 2 for Simple Transparent Adversarial Examples
Figure 3 for Simple Transparent Adversarial Examples
Figure 4 for Simple Transparent Adversarial Examples
* 14 pages, 9 figures, Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems 
  Access Paper or Ask Questions

Vision Transformers are Robust Learners


May 18, 2021
Sayak Paul, Pin-Yu Chen

Figure 1 for Vision Transformers are Robust Learners
Figure 2 for Vision Transformers are Robust Learners
Figure 3 for Vision Transformers are Robust Learners
Figure 4 for Vision Transformers are Robust Learners

  Access Paper or Ask Questions

High-Robustness, Low-Transferability Fingerprinting of Neural Networks


May 14, 2021
Siyue Wang, Xiao Wang, Pin-Yu Chen, Pu Zhao, Xue Lin

Figure 1 for High-Robustness, Low-Transferability Fingerprinting of Neural Networks
Figure 2 for High-Robustness, Low-Transferability Fingerprinting of Neural Networks
Figure 3 for High-Robustness, Low-Transferability Fingerprinting of Neural Networks
Figure 4 for High-Robustness, Low-Transferability Fingerprinting of Neural Networks
* ICLR 2021 Workshop on Security and Safety in Machine Learning Systems 
  Access Paper or Ask Questions

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training


Apr 21, 2021
Chia-Yu Chen, Jiamin Ni, Songtao Lu, Xiaodong Cui, Pin-Yu Chen, Xiao Sun, Naigang Wang, Swagath Venkataramani, Vijayalakshmi Srinivasan, Wei Zhang, Kailash Gopalakrishnan

Figure 1 for ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Figure 2 for ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Figure 3 for ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Figure 4 for ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
* NeurIPS2020 accepted https://proceedings.neurips.cc/paper/2020/hash/9d58963592071dbf38a0fa114269959c-Abstract.html 
  Access Paper or Ask Questions

Gi and Pal Scores: Deep Neural Network Generalization Statistics


Apr 08, 2021
Yair Schiff, Brian Quanz, Payel Das, Pin-Yu Chen

Figure 1 for Gi and Pal Scores: Deep Neural Network Generalization Statistics
Figure 2 for Gi and Pal Scores: Deep Neural Network Generalization Statistics
* Accepted to RobustML Workshop at ICLR 2021 
  Access Paper or Ask Questions

Towards creativity characterization of generative models via group-based subset scanning


Apr 01, 2021
Celia Cintas, Payel Das, Brian Quanz, Skyler Speakman, Victor Akinwande, Pin-Yu Chen

Figure 1 for Towards creativity characterization of generative models via group-based subset scanning
Figure 2 for Towards creativity characterization of generative models via group-based subset scanning
* Synthetic Data Generation Workshop at ICLR'21 
  Access Paper or Ask Questions