ICLR

Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning

Elan Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Sami Abu-El-Haija, Bryan Perozzi, Greg Ver Steeg, Aram Galstyan

Comments To appear in ICLR 2021

Efficient Certified Defenses Against Patch Attacks on Image Classifiers

Jan Hendrik Metzen, Maksym Yatsura

Comments accepted at ICLR 2021

SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments

Glen Berseth, Daniel Geng, Coline Devin, Nicholas Rhinehart, Chelsea Finn, Dinesh Jayaraman, Sergey Levine

Comments ICLR 2021

Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy

Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka

Comments Accepted to International Conference on Learning Representations (ICLR) 2021 (Spotlight presentation)

Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU

Patrick Kidger, Terry Lyons

Comments Published at ICLR 2021

Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity

Jang-Hyun Kim, Wonho Choo, Hosan Jeong, Hyun Oh Song

Comments Published at ICLR 2021 (Oral)

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation

Angtian Wang, Adam Kortylewski, Alan Yuille

Comments Accepted by ICLR 2021. Code is publicly available

Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments

Daochen Zha, Wenye Ma, Lei Yuan, Xia Hu, Ji Liu

Comments Accepted by ICLR 2021

Trusted Multi-View Classification

Zongbo Han, Changqing Zhang, Huazhu Fu, Joey Tianyi Zhou

Comments Accepted by ICLR 2021

Isometric Propagation Network for Generalized Zero-shot Learning

Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Xuanyi Dong, Chengqi Zhang

Comments Accepted by ICLR 2021

Structured Neural Summarization

Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt

Comments Published in ICLR 2019 https://openreview.net/forum?id=H1ersoRqtm

Graph Coarsening with Neural Networks

Chen Cai, Dingkang Wang, Yusu Wang

Comments International Conference on Learning Representations 2021

Directed Acyclic Graph Neural Networks

Veronika Thost, Jie Chen

Comments ICLR 2021. Code is available at https://github.com/vthost/DAGNN

Efficient Conformal Prediction via Cascaded Inference with Expanded Admission

Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

Comments ICLR 2021. Revision of "Relaxed Conformal Prediction Cascades for Efficient Inference Over Many Labels"

RTFM: Generalising to Novel Environment Dynamics via Reading

Victor Zhong, Tim Rocktäschel, Edward Grefenstette

Comments ICLR 2020; 17 pages, 13 figures

Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective

Helong Zhou, Liangchen Song, Jiajie Chen, Ye Zhou, Guoli Wang, Junsong Yuan, Qian Zhang

Comments ICLR 2021

Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms

Maruan Al-Shedivat, Jennifer Gillenwater, Eric Xing, Afshin Rostamizadeh

Comments ICLR 2021. Code: https://github.com/alshedivat/fedpa

Improving VAEs' Robustness to Adversarial Attack

Matthew Willetts, Alexander Camuto, Tom Rainforth, Stephen Roberts, Chris Holmes

Comments Main paper of 9 pages, followed by appendix

Journal ref International Conference on Learning Representations (ICLR) 2021

On the Origin of Implicit Regularization in Stochastic Gradient Descent

Samuel L. Smith, Benoit Dherin, David G. T. Barrett, Soham De

Comments Accepted as a conference paper at ICLR 2021

Disambiguating Symbolic Expressions in Informal Documents

Dennis Müller, Cezary Kaliszyk

Comments ICLR 2021 conference paper

NBDT: Neural-Backed Decision Trees

Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Henry Jin, Suzanne Petryk, Sarah Adel Bargal, Joseph E. Gonzalez

Comments 8 pages, 7 figures, accepted to ICLR 2021

Shape or Texture: Understanding Discriminative Features in CNNs

Md Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Bjorn Ommer, Konstantinos G. Derpanis, Neil Bruce

Comments Accepted to ICLR 2021

Characterizing signal propagation to close the performance gap in unnormalized ResNets

Andrew Brock, Soham De, Samuel L. Smith

Comments Published as a conference paper at ICLR 2021

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma

Comments 19 pages, 14 figures, ICLR 2021

Understanding and Improving Lexical Choice in Non-Autoregressive Translation

Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu

Comments ICLR 2021

Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

Jiahui Yu, Wei Han, Anmol Gulati, Chung-Cheng Chiu, Bo Li, Tara N. Sainath, Yonghui Wu, Ruoming Pang

Comments Accepted in ICLR 2021

Revisiting Locally Supervised Learning: an Alternative to End-to-end Training

Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang

Comments Accepted by ICLR 2021

Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling

Benedikt Boecking, Willie Neiswanger, Eric Xing, Artur Dubrawski

Comments Accepted as a conference paper at ICLR 2021

C-Learning: Horizon-Aware Cumulative Accessibility Estimation

Panteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner, Anthony L. Caterini, Jesse C. Cresswell, Tong Li, Animesh Garg

Comments Accepted at ICLR 2021

NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size

Xuanyi Dong, Lu Liu, Katarzyna Musial, Bogdan Gabrys

Comments Accepted to IEEE TPAMI 2021, an extended version of NAS-Bench-201 (ICLR 2020) [arXiv:2001.00326]