ICML

VEGN: Variant Effect Prediction with Graph Neural Networks

Jun Cheng, Carolin Lawrence, Mathias Niepert

Comments Accepted at Workshop on Computational Biology, co-located with the 38th International Conference on Machine Learning

Reliable Graph Neural Network Explanations Through Adversarial Training

Donald Loveland, Shusen Liu, Bhavya Kailkhura, Anna Hiszpanski, Yong Han

Comments 4 pages, 3 figures, ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Decomposed Mutual Information Estimation for Contrastive Representation Learning

Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Phil Bachman, Remi Tachet

Comments ICML 2021

What will it take to generate fairness-preserving explanations?

Jessica Dai, Sohini Upadhyay, Stephen H. Bach, Himabindu Lakkaraju

Comments Presented at ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

On the (Un-)Avoidability of Adversarial Examples

Sadia Chowdhury, Ruth Urner

Comments ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Optimal Counterfactual Explanations in Tree Ensembles

Axel Parmentier, Thibaut Vidal

Comments Authors Accepted Manuscript (AAM), to be published in the Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021. Additional typo corrections. Open source code available at https://github.com/vidalt/OCEAN

Prior Image-Constrained Reconstruction using Style-Based Generative Models

Varun A. Kelkar, Mark A. Anastasio

Comments Accepted for publication at the International Conference on Machine Learning (ICML) 2021

Graph Mixture Density Networks

Federico Errica, Davide Bacciu, Alessio Micheli

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139 (2021)

Learning to Generate Noise for Multi-Attack Robustness

Divyam Madaan, Jinwoo Shin, Sung Ju Hwang

Comments Accepted to ICML 2021. Code available at https://github.com/divyam3897/MNG_AC

Towards Understanding and Mitigating Social Biases in Language Models

Paul Pu Liang, Chiyu Wu, Louis-Philippe Morency, Ruslan Salakhutdinov

Comments ICML 2021, code available at https://github.com/pliang279/LM_bias

Towards Fully Interpretable Deep Neural Networks: Are We There Yet?

Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee

Comments Presented at the ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

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

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

Comments ICML 2021

Dimensionality Reduction for Sum-of-Distances Metric

Zhili Feng, Praneeth Kacham, David P. Woodruff

Comments 27 pages, 2 figures. To appear at ICML 2021

Evaluation of Saliency-based Explainability Method

Sam Zabdiel Sunder Samuel, Vidhya Kamakshi, Namrata Lodhi, Narayanan C Krishnan

Comments Accepted at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI, 2021

Density Constrained Reinforcement Learning

Zengyi Qin, Yuxiao Chen, Chuchu Fan

Comments Accepted by ICML, 2021

Alternative Microfoundations for Strategic Classification

Meena Jagadeesan, Celestine Mendler-Dünner, Moritz Hardt

Comments Accepted for publication at ICML 2021

Reimagining GNN Explanations with ideas from Tabular Data

Anjali Singh, Shamanth R Nayak K, Balaji Ganesan

Comments 4 pages, 8 figures, XAI Workshop at ICML 2021

EfficientNetV2: Smaller Models and Faster Training

Mingxing Tan, Quoc V. Le

Comments ICML 2021

Journal ref International Conference on Machine Learning, 2021

Optimizing Black-box Metrics with Iterative Example Weighting

Gaurush Hiranandani, Jatin Mathur, Harikrishna Narasimhan, Mahdi Milani Fard, Oluwasanmi Koyejo

Comments The paper to appear at ICML 2021. This version includes the camera-ready edits. 42 pages, 2 figures, and 7 tables

Gradient-Based Interpretability Methods and Binarized Neural Networks

Amy Widdicombe, Simon J. Julier

Comments Accepted at the ICML 2021 Workshop on Theoretic Foundation, Criticism & Application Trend of Explainable AI

Training Data Subset Selection for Regression with Controlled Generalization Error

Durga Sivasubramanian, Rishabh Iyer, Ganesh Ramakrishnan, Abir De

Journal ref ICML 2021

Learning Under Delayed Feedback: Implicitly Adapting to Gradient Delays

Rotem Zamir Aviv, Ido Hakimi, Assaf Schuster, Kfir Y. Levy

Comments to be published in ICML 2021

Near-Optimal Linear Regression under Distribution Shift

Qi Lei, Wei Hu, Jason D. Lee

Comments ICML 2021

Learned Interpretable Residual Extragradient ISTA for Sparse Coding

Lin Kong, Wei Sun, Fanhua Shang, Yuanyuan Liu, Hongying Liu

Comments Accepted for presentation at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Oneshot Differentially Private Top-k Selection

Gang Qiao, Weijie J. Su, Li Zhang

Comments Accepted to ICML 2021

This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks

Adrian Hoffmann, Claudio Fanconi, Rahul Rade, Jonas Kohler

Journal ref ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Perceiver: General Perception with Iterative Attention

Andrew Jaegle, Felix Gimeno, Andrew Brock, Andrew Zisserman, Oriol Vinyals, Joao Carreira

Comments ICML 2021

LogME: Practical Assessment of Pre-trained Models for Transfer Learning

Kaichao You, Yong Liu, Jianmin Wang, Mingsheng Long

Comments 13 pages (ICML 2021 camera ready version)

Meta-Thompson Sampling

Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvari

Comments Proceedings of the 38th International Conference on Machine Learning

On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise

Jie Shen

Comments V2 and V3 polished writing; accepted to ICML 2021