ICLR

An extensible Benchmarking Graph-Mesh dataset for studying Steady-State Incompressible Navier-Stokes Equations

Florent Bonnet, Jocelyn Ahmed Mazari, Thibaut Munzer, Pierre Yser, Patrick Gallinari

Comments ICLR 2022 Workshop on Geometrical and Topological Representation Learning

Journal ref ICLR 2022 Workshop on Geometrical and Topological Representation Learning

Multi-scale Physical Representations for Approximating PDE Solutions with Graph Neural Operators

Léon Migus, Yuan Yin, Jocelyn Ahmed Mazari, Patrick Gallinari

Comments ICLR 2022 Workshop on Geometrical and Topological Representation Learning

Journal ref ICLR 2022 Workshop on Geometrical and Topological Representation Learning

Measuring and Improving the Use of Graph Information in Graph Neural Networks

Yifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma, Hongzhi Chen, Ming-Chang Yang

Comments This paper has been published in ICLR 2020. Code and Dataset can be found here: https://github.com/yifan-h/CS-GNN

Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming

Sachin Konan, Esmaeil Seraj, Matthew Gombolay

Comments The first two authors contributed equally to this work (Published in ICLR 2022)

Journal ref International Conference on Learning Representations 2022

Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs

Jaewoong Choi, Junho Lee, Changyeon Yoon, Jung Ho Park, Geonho Hwang, Myungjoo Kang

Comments 24 pages, 19 figures

Journal ref International Conference on Learning Representations, 2022

Learning Towards the Largest Margins

Xiong Zhou, Xianming Liu, Deming Zhai, Junjun Jiang, Xin Gao, Xiangyang Ji

Comments ICLR 2022

Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks

Haorui Wang, Haoteng Yin, Muhan Zhang, Pan Li

Comments ICLR 2022; The revised version updates some notation mistakes and discusses on the stability of PE in different settings; code available at https://github.com/Graph-COM/PEG

Discriminative Similarity for Data Clustering

Yingzhen Yang, Ping Li

Comments Published at ICLR 2022; this article supersedes arXiv:1709.01231

Modeling Emergent Lexicon Formation with a Self-Reinforcing Stochastic Process

Brendon Boldt, David Mortensen

Comments Published as workshop paper at EmeCom at ICLR 2022, 8 pages, 14 figures

Imitation Learning for Generalizable Self-driving Policy with Sim-to-real Transfer

Zoltán Lőrincz, Márton Szemenyei, Róbert Moni

Comments Accepted by ICLR 2022 Workshop on Generalizable Policy Learning in Physical World. Source code is available at: https://github.com/lzoltan35/duckietown_imitation_learning

Transformer-Based Multi-modal Proposal and Re-Rank for Wikipedia Image-Caption Matching

Nicola Messina, Davide Alessandro Coccomini, Andrea Esuli, Fabrizio Falchi

Comments Accepted for publication at the Wiki-M3L workshop, co-located with ICLR 2022

Practical Deepfake Detection: Vulnerabilities in Global Contexts

Yang A. Chuming, Daniel J. Wu, Ken Hong

Comments 6 pages, 6 figures, presented as a workshop paper at Responsible AI @ ICLR 2021

Learning to Share in Multi-Agent Reinforcement Learning

Yuxuan Yi, Ge Li, Yaowei Wang, Zongqing Lu

Comments ICLR 2022 Workshop on Gamification and Multiagent Solutions, Best Cooperative AI Paper Award

GradSign: Model Performance Inference with Theoretical Insights

Zhihao Zhang, Zhihao Jia

Journal ref The Tenth International Conference on Learning Representations (ICLR 2022)

Towards Robustness to Label Noise in Text Classification via Noise Modeling

Siddhant Garg, Goutham Ramakrishnan, Varun Thumbe

Comments Accepted at CIKM'21 (30th ACM International Conference on Information & Knowledge Management). Accepted at ICLR 2021 RobustML and S2D-OLAD Workshops

A Theoretical Analysis of the Number of Shots in Few-Shot Learning

Tianshi Cao, Marc Law, Sanja Fidler

Comments 15 pages incl. appendix, 6 figures

Journal ref 8th International Conference on Learning Representations 2020, Addis Ababa, Ethiopia

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

Wensi Tang, Guodong Long, Lu Liu, Tianyi Zhou, Michael Blumenstein, Jing Jiang

Comments Accepted by ICLR 2022

Journal ref The Tenth International Conference on Learning Representations(ICLR 2022)

Multimeasurement Generative Models

Saeed Saremi, Rupesh Kumar Srivastava

Comments Our code is publicly available at https://github.com/nnaisense/mems

Journal ref International Conference on Learning Representations, 2022

Solving Inverse Problems in Medical Imaging with Score-Based Generative Models

Yang Song, Liyue Shen, Lei Xing, Stefano Ermon

Comments Published at ICLR 2022

Missingness Bias in Model Debugging

Saachi Jain, Hadi Salman, Eric Wong, Pengchuan Zhang, Vibhav Vineet, Sai Vemprala, Aleksander Madry

Comments Published at ICLR 2022

Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums

Rui Pan, Haishan Ye, Tong Zhang

Comments Published at ICLR 2022

Fast Model Editing at Scale

Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, Christopher D. Manning

Comments ICLR 2022. View implementation and additional project info at https://sites.google.com/view/mend-editing

Context-Aware Sparse Deep Coordination Graphs

Tonghan Wang, Liang Zeng, Weijun Dong, Qianlan Yang, Yang Yu, Chongjie Zhang

Journal ref ICLR 2022 Spotlight

Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation

Yingwei Pan, Yehao Li, Yiheng Zhang, Qi Cai, Fuchen Long, Zhaofan Qiu, Ting Yao, Tao Mei

Comments Accepted by ICLR 2022 Workshop on Generalizable Policy Learning in Physical World. Top-performing systems for both no interaction and no restriction tracks in SAPIEN ManiSkill Challenge 2021. The source code and model are publicly available at: https://github.com/caiqi/Silver-Bullet-3D/

Practical Conditional Neural Processes Via Tractable Dependent Predictions

Stratis Markou, James Requeima, Wessel P. Bruinsma, Anna Vaughan, Richard E. Turner

Comments 23 pages; accepted to the 10th International Conference on Learning Representations (ICLR 2022)

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Xiaojian Ma, Weili Nie, Zhiding Yu, Huaizu Jiang, Chaowei Xiao, Yuke Zhu, Song-Chun Zhu, Anima Anandkumar

Comments ICLR 2022; Code: https://github.com/NVlabs/RelViT

Network insensitivity to parameter noise via adversarial regularization

Julian Büchel, Fynn Faber, Dylan R. Muir

Journal ref ICLR 2022 (https://openreview.net/forum?id=-8sBpe7rDiV)

R4D: Utilizing Reference Objects for Long-Range Distance Estimation

Yingwei Li, Tiffany Chen, Maya Kabkab, Ruichi Yu, Longlong Jing, Yurong You, Hang Zhao

Comments ICLR 2022

CoCon: A Self-Supervised Approach for Controlled Text Generation

Alvin Chan, Yew-Soon Ong, Bill Pung, Aston Zhang, Jie Fu

Comments ICLR 2021 Camera-Ready

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

Victor Schmidt, Alexandra Sasha Luccioni, Mélisande Teng, Tianyu Zhang, Alexia Reynaud, Sunand Raghupathi, Gautier Cosne, Adrien Juraver, Vahe Vardanyan, Alex Hernandez-Garcia, Yoshua Bengio

Journal ref ICLR 2022