ICLR

Continual learning with hypernetworks

Johannes von Oswald, Christian Henning, Benjamin F. Grewe, João Sacramento

Comments Published at ICLR 2020

Expressiveness and Approximation Properties of Graph Neural Networks

Floris Geerts, Juan L. Reutter

Comments 43 pages, accepted as oral presentation at ICLR 2022: https://openreview.net/forum?id=wIzUeM3TAU

ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification

Kunze Wang, Soyeon Caren Han, Siqu Long, Josiah Poon

Comments ICLR 2022 on DLG4NLP

Divergence-aware Federated Self-Supervised Learning

Weiming Zhuang, Yonggang Wen, Shuai Zhang

Comments ICLR'22

A Siren Song of Open Source Reproducibility

Edward Raff, Andrew L. Farris

Comments To be presented at the ML Evaluation Standards Workshop at ICLR 2022

Evaluating the Adversarial Robustness for Fourier Neural Operators

Abolaji D. Adesoji, Pin-Yu Chen

Comments Accepted to Workshop on Socially Responsible Machine Learning (SRML), co-located with ICLR 2022

Neural Logic Analogy Learning

Yujia Fan, Yongfeng Zhang

Comments In Proceedings of the ICLR 2022 PAIR2Struct Workshop

Attention-Free Keyword Spotting

Mashrur M. Morshed, Ahmad Omar Ahsan

Comments 5 pages: Accepted at PML4DC workshop in ICLR 2022

Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design

Ye Yuan, Yuda Song, Zhengyi Luo, Wen Sun, Kris Kitani

Comments ICLR 2022 (Oral). Project page: https://sites.google.com/view/transform2act. Code: https://github.com/Khrylx/Transform2Act

Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective

Qi Lyu, Xiao Fu, Weiran Wang, Songtao Lu

Comments Accepted to ICLR 2022 Spotlight, 37 pages, 11 figures

Does the Market of Citations Reward Reproducible Work?

Edward Raff

Comments To be presented at the ML Evaluation Standards Workshop at ICLR 2022

Using Multiple Self-Supervised Tasks Improves Model Robustness

Matthew Lawhon, Chengzhi Mao, Junfeng Yang

Comments Accepted to ICLR 2022 Workshop on PAIR^2Struct: Privacy, Accountability, Interpretability, Robustness, Reasoning on Structured Data

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Yu Meng, Chenyan Xiong, Payal Bajaj, Saurabh Tiwary, Paul Bennett, Jiawei Han, Xia Song

Comments ICLR 2022. (Code and Models: https://github.com/microsoft/AMOS)

Knowledge Infused Decoding

Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Hassan Awadallah

Comments In ICLR 2022

On the Limitations of Multimodal VAEs

Imant Daunhawer, Thomas M. Sutter, Kieran Chin-Cheong, Emanuele Palumbo, Julia E. Vogt

Comments ICLR 2022 camera-ready version

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

Ali Kavis, Kfir Yehuda Levy, Volkan Cevher

Comments 27 pages, acccepted to ICLR 2022

Towards Designing and Exploiting Generative Networks for Neutrino Physics Experiments using Liquid Argon Time Projection Chambers

Paul Lutkus, Taritree Wongjirad, Shuchin Aeron

Comments Published as a conference paper at ICLR 2021 SimDL Workshop

Considerations for Multilingual Wikipedia Research

Isaac Johnson, Emily Lescak

Comments Accepted to Wiki-M3L workshop as part of ICLR 2022

Transfer RL across Observation Feature Spaces via Model-Based Regularization

Yanchao Sun, Ruijie Zheng, Xiyao Wang, Andrew Cohen, Furong Huang

Comments In the 10th International Conference on Learning Representations (ICLR 2022)

Collective control of modular soft robots via embodied Spiking Neural Cellular Automata

Giorgia Nadizar, Eric Medvet, Stefano Nichele, Sidney Pontes-Filho

Comments Workshop on "From Cells to Societies: Collective Learning across Scales" at the International Conference on Learning Representations (Cells2Societies@ICLR)

Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation

Junhyun Nam, Jaehyung Kim, Jaeho Lee, Jinwoo Shin

Comments ICLR 2022 camera ready

Benchmarking Generative Latent Variable Models for Speech

Jakob D. Havtorn, Lasse Borgholt, Søren Hauberg, Jes Frellsen, Lars Maaløe

Comments Accepted at the 2022 ICLR workshop on Deep Generative Models for Highly Structured Data (https://deep-gen-struct.github.io)

Representational Continuity for Unsupervised Continual Learning

Divyam Madaan, Jaehong Yoon, Yuanchun Li, Yunxin Liu, Sung Ju Hwang

Comments Accepted to ICLR (Oral) 2022. Code available at https://github.com/divyam3897/UCL

Directional Message Passing for Molecular Graphs

Johannes Gasteiger, Janek Groß, Stephan Günnemann

Comments Published as a conference paper at ICLR 2020. Author name changed from Johannes Klicpera to Johannes Gasteiger

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

Johannes Gasteiger, Aleksandar Bojchevski, Stephan Günnemann

Comments Published as a conference paper at ICLR 2019. Author name changed from Johannes Klicpera to Johannes Gasteiger

Journal ref International Conference on Learning Representations (ICLR), New Orleans, LA, USA, 2019

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

Zhisheng Xiao, Karsten Kreis, Arash Vahdat

Comments ICLR 2022 (Spotlight)

Learning to Superoptimize Real-world Programs

Alex Shypula, Pengcheng Yin, Jeremy Lacomis, Claire Le Goues, Edward Schwartz, Graham Neubig

Comments Best Paper, ICLR 2022 Deep Learning for Code workshop

Probabilistic Implicit Scene Completion

Dongsu Zhang, Changwoon Choi, Inbum Park, Young Min Kim

Comments Accepted to ICLR 2022 as spotlight, code available at https://github.com/96lives/gca

Language-driven Semantic Segmentation

Boyi Li, Kilian Q. Weinberger, Serge Belongie, Vladlen Koltun, René Ranftl

Comments ICLR 2022

IGLU: Efficient GCN Training via Lazy Updates

S Deepak Narayanan, Aditya Sinha, Prateek Jain, Purushottam Kar, Sundararajan Sellamanickam

Comments Published as Conference Paper at ICLR 2022, 36 Pages