ICLR

GraphTSNE: A Visualization Technique for Graph-Structured Data

Yao Yang Leow, Thomas Laurent, Xavier Bresson

Comments Published as a workshop paper at ICLR 2019

DARTS: Differentiable Architecture Search

Hanxiao Liu, Karen Simonyan, Yiming Yang

Comments Published at ICLR 2019; Code and pretrained models available at https://github.com/quark0/darts

Distributed generation of privacy preserving data with user customization

Xiao Chen, Thomas Navidi, Stefano Ermon, Ram Rajagopal

Comments accepted in ICLR 2019 SafeML workshop

Systematic Generalization: What Is Required and Can It Be Learned?

Dzmitry Bahdanau, Shikhar Murty, Michael Noukhovitch, Thien Huu Nguyen, Harm de Vries, Aaron Courville

Comments Published as a conference paper at ICLR 2019

Deep learning generalizes because the parameter-function map is biased towards simple functions

Guillermo Valle-Pérez, Chico Q. Camargo, Ard A. Louis

Comments Published as a conference paper at ICLR 2019

Spherical CNNs

Taco S. Cohen, Mario Geiger, Jonas Koehler, Max Welling

Comments Proceedings of the 6th International Conference on Learning Representations (ICLR), 2018

Journal ref Proceedings of the International Conference on Learning Representations, 2018

Steerable CNNs

Taco S. Cohen, Max Welling

Journal ref Proceedings of the International Conference on Learning Representations, 2017

Transformation Properties of Learned Visual Representations

Taco S. Cohen, Max Welling

Comments T.S. Cohen & M. Welling, Transformation Properties of Learned Visual Representations. In International Conference on Learning Representations (ICLR), 2015

Journal ref Proceedings of the International Conference on Learning Representations, 2015

On the Convergence of Adam and Beyond

Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

Comments Appeared in ICLR 2018

Bridging Adversarial Robustness and Gradient Interpretability

Beomsu Kim, Junghoon Seo, Taegyun Jeon

Comments Accepted at the 2019 ICLR Workshop on Safe Machine Learning: Specification, Robustness, and Assurance (SafeML 2019)

Adaptive Gradient Methods with Dynamic Bound of Learning Rate

Liangchen Luo, Yuanhao Xiong, Yan Liu, Xu Sun

Comments Accepted to ICLR 2019. arXiv admin note: text overlap with arXiv:1904.09237 by other authors

Preferences Implicit in the State of the World

Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca Dragan

Comments Published at ICLR 2019

Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids

Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B. Tenenbaum, Antonio Torralba

Comments Accepted to ICLR 2019. Project Page: http://dpi.csail.mit.edu Video: https://www.youtube.com/watch?v=FrPpP7aW3Lg

Multi-View Data Generation Without View Supervision

Mickaël Chen, Ludovic Denoyer, Thierry Artières

Comments Published as a conference paper at ICLR 2018

Graph Wavelet Neural Network

Bingbing Xu, Huawei Shen, Qi Cao, Yunqi Qiu, Xueqi Cheng

Journal ref ICLR(2019)

FlowQA: Grasping Flow in History for Conversational Machine Comprehension

Hsin-Yuan Huang, Eunsol Choi, Wen-tau Yih

Comments 15 pages, Published at ICLR 2019

Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces

Senthil Purushwalkam, Abhinav Gupta, Danny M. Kaufman, Bryan Russell

Comments Accepted for publication at the International Conference on Learning Representations (ICLR) 2019

Spatio-Temporal Deep Graph Infomax

Felix L. Opolka, Aaron Solomon, Cătălina Cangea, Petar Veličković, Pietro Liò, R Devon Hjelm

Comments 6 pages, 2 figures, Representation Learning on Graphs and Manifolds Workshop of the International Conference on Learning Representations (ICLR)

Learning to Design RNA

Frederic Runge, Danny Stoll, Stefan Falkner, Frank Hutter

Comments Published as a conference paper at the International Conference on Learning Representations 2019 (ICLR19)

Selfless Sequential Learning

Rahaf Aljundi, Marcus Rohrbach, Tinne Tuytelaars

Comments Published as a conference paper at ICLR 2019

Knowledge Flow: Improve Upon Your Teachers

Iou-Jen Liu, Jian Peng, Alexander G. Schwing

Comments Accepted to ICLR 2019

DeepSphere: towards an equivariant graph-based spherical CNN

Michaël Defferrard, Nathanaël Perraudin, Tomasz Kacprzak, Raphael Sgier

Comments published at the ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds. arXiv admin note: text overlap with arXiv:1810.12186

Measuring Compositionality in Representation Learning

Jacob Andreas

Comments ICLR 2019

Neural Networks for Modeling Source Code Edits

Rui Zhao, David Bieber, Kevin Swersky, Daniel Tarlow

Comments Deanonymized version of ICLR 2019 submission

Neural Program Repair by Jointly Learning to Localize and Repair

Marko Vasic, Aditya Kanade, Petros Maniatis, David Bieber, Rishabh Singh

Comments ICLR 2019

Neural Speed Reading with Structural-Jump-LSTM

Christian Hansen, Casper Hansen, Stephen Alstrup, Jakob Grue Simonsen, Christina Lioma

Comments 10 pages

Journal ref 7th International Conference on Learning Representations (ICLR) 2019

Phase-aware Speech Enhancement with Deep Complex U-Net

Hyeong-Seok Choi, Jang-Hyun Kim, Jaesung Huh, Adrian Kim, Jung-Woo Ha, Kyogu Lee

Comments Significant error was found in data processing step, therefore will be retracted from International Conference on Learning Representations (ICLR) 2019. It is not recommended to read current version

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

Wieland Brendel, Matthias Bethge

Comments Published as a conference paper at the Seventh International Conference on Learning Representations (ICLR 2019)

Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking

Aleksandar Bojchevski, Stephan Günnemann

Comments Updated: ICLR 2018 camera-ready version

Journal ref International Conference on Learning Representations, ICLR 2018

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

Dan Hendrycks, Thomas Dietterich

Comments ICLR 2019 camera-ready; datasets available at https://github.com/hendrycks/robustness ; this article supersedes arXiv:1807.01697