ICML

Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis

Hejie Cui, Wei Dai, Yanqiao Zhu, Xiaoxiao Li, Lifang He, Carl Yang

Comments Previous version presented at icml-imlh 2021 (no proceedings, archived at 2107.05097), this version is accepted to miccai 2022

Hyper-Representations for Pre-Training and Transfer Learning

Konstantin Schürholt, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth

Journal ref First Workshop of Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022, Baltimore, Maryland, USA, PMLR 162, 2022

DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

Samyam Rajbhandari, Conglong Li, Zhewei Yao, Minjia Zhang, Reza Yazdani Aminabadi, Ammar Ahmad Awan, Jeff Rasley, Yuxiong He

Comments This paper is published at ICML 2022: https://proceedings.mlr.press/v162/rajbhandari22a

NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework

Xingcheng Yao, Yanan Zheng, Xiaocong Yang, Zhilin Yang

Comments 14 pages, 5 figures

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:25438-25451, 2022

Function-space Inference with Sparse Implicit Processes

Simón Rodríguez Santana, Bryan Zaldivar, Daniel Hernández-Lobato

Comments Published at ICML 2022 (long oral presentation). Code available at https://github.com/simonrsantana/sparse-implicit-processes

Analyzing and Mitigating Interference in Neural Architecture Search

Jin Xu, Xu Tan, Kaitao Song, Renqian Luo, Yichong Leng, Tao Qin, Tie-Yan Liu, Jian Li

Comments ICML 2022, Spotlight

Multilingual Disinformation Detection for Digital Advertising

Zofia Trstanova, Nadir El Manouzi, Maryline Chen, Andre L. V. da Cunha, Sergei Ivanov

Comments Disinformation Countermeasures and Machine Learning Workshop at ICML 2022

The Neural Race Reduction: Dynamics of Abstraction in Gated Networks

Andrew M. Saxe, Shagun Sodhani, Sam Lewallen

Comments ICML 2022; 23 pages; 10 figures

Slimmable Quantum Federated Learning

Won Joon Yun, Jae Pyoung Kim, Soyi Jung, Jihong Park, Mehdi Bennis, Joongheon Kim

Comments ICML 2022 Workshop on Dynamic Neural Networks (Spotlight Paper)

Revisiting Hotels-50K and Hotel-ID

Aarash Feizi, Arantxa Casanova, Adriana Romero-Soriano, Reihaneh Rabbany

Comments ICML 2022 DataPerf Workshop

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

Sadegh Farhadkhani, Rachid Guerraoui, Lê-Nguyên Hoang, Oscar Villemaud

Comments arXiv admin note: text overlap with arXiv:2106.02398

Journal ref ICML 2022

Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization

Mariia Seleznova, Gitta Kutyniok

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:19522-19560, 2022

Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations

Haoran Xu, Xianyuan Zhan, Honglei Yin, Huiling Qin

Comments ICML 2022, code at https://github.com/ryanxhr/DWBC

Pretraining a Neural Network before Knowing Its Architecture

Boris Knyazev

Comments Accepted at ICML 2022 Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward, source code is available at https://github.com/facebookresearch/ppuda

Sample Efficient Learning of Predictors that Complement Humans

Mohammad-Amin Charusaie, Hussein Mozannar, David Sontag, Samira Samadi

Comments ICML 2022

Hybrid Physical-Neural ODEs for Fast N-body Simulations

Denise Lanzieri, François Lanusse, Jean-Luc Starck

Comments Accepted at the ICML 2022 Workshop on Machine Learning for Astrophysics. Updated version with link to the source code

Diversified Adversarial Attacks based on Conjugate Gradient Method

Keiichiro Yamamura, Haruki Sato, Nariaki Tateiwa, Nozomi Hata, Toru Mitsutake, Issa Oe, Hiroki Ishikura, Katsuki Fujisawa

Comments Proceedings of the 39th International Conference on Machine Learning (ICML 2022)

FORML: Learning to Reweight Data for Fairness

Bobby Yan, Skyler Seto, Nicholas Apostoloff

Comments 9 pages, 2 figures, Presented at ICML 2022 DataPerf Workshop

A Convolutional Neural Network Approach to Supernova Time-Series Classification

Helen Qu, Masao Sako, Anais Moller, Cyrille Doux

Comments Accepted at the ICML 2022 Workshop on Machine Learning for Astrophysics

Towards Trustworthy Healthcare AI: Attention-Based Feature Learning for COVID-19 Screening With Chest Radiography

Kai Ma, Pengcheng Xi, Karim Habashy, Ashkan Ebadi, Stéphane Tremblay, Alexander Wong

Comments Accepted to 39th International Conference on Machine Learning, Workshop on Healthcare AI and COVID-19

Similarity of Pre-trained and Fine-tuned Representations

Thomas Goerttler, Klaus Obermayer

Comments Workshop of Updatable Machine Learning at ICML 2022

Lazy Estimation of Variable Importance for Large Neural Networks

Yue Gao, Abby Stevens, Rebecca Willet, Garvesh Raskutti

Comments Accepted to ICML'22

Time Is MattEr: Temporal Self-supervision for Video Transformers

Sukmin Yun, Jaehyung Kim, Dongyoon Han, Hwanjun Song, Jung-Woo Ha, Jinwoo Shin

Comments Accepted to ICML 2022. Code is available at https://github.com/alinlab/temporal-selfsupervision

Latent Outlier Exposure for Anomaly Detection with Contaminated Data

Chen Qiu, Aodong Li, Marius Kloft, Maja Rudolph, Stephan Mandt

Comments To appear in ICML 2022

Journal ref Proceedings of the 39th International Conference on Machine Learning, 2022, volume:162, pages:18153--18167

GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks

Yixuan He, Quan Gan, David Wipf, Gesine Reinert, Junchi Yan, Mihai Cucuringu

Comments ICML 2022 spotlight; 32 pages (9 pages for main text)

Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs

Yikang Zhang, Zhuo Chen, Zhao Zhong

Comments ICML

Selection Bias Induced Spurious Correlations in Large Language Models

Emily McMilin

Comments 8 pages, 5 figures, Published at the ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability

Towards Learning Self-Organized Criticality of Rydberg Atoms using Graph Neural Networks

Simon Ohler, Daniel Brady, Winfried Lötzsch, Michael Fleischhauer, Johannes S. Otterbach

Journal ref 2nd AI4Science Workshop at the 39th International Conference on Machine Learning (ICML), 2022

Robust Training of Neural Networks Using Scale Invariant Architectures

Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar

Comments 36 pages, 7 figures; ICML 2022

Streaming Algorithms for Support-Aware Histograms

Justin Y. Chen, Piotr Indyk, Tal Wagner

Comments Appearing in ICML'22