ICLR

Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning

Akanksha Atrey, Kaleigh Clary, David Jensen

Comments Published at ICLR 2020

BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning

Yeming Wen, Dustin Tran, Jimmy Ba

Journal ref Eighth International Conference on Learning Representations (ICLR 2020)

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Michael Rabbat

Comments Accepted to ICLR 2020

Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

Tianyu Pang, Kun Xu, Jun Zhu

Comments ICLR 2020

Uncertainty-guided Continual Learning with Bayesian Neural Networks

Sayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell, Marcus Rohrbach

Comments Accepted at ICLR 2020

Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness

Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, Jun Zhu

Comments ICLR 2020

Language GANs Falling Short

Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau, Laurent Charlin

Journal ref ICLR 2020 - Proceedings of the Seventh International Conference on Learning Representation

Tree-structured Attention with Hierarchical Accumulation

Xuan-Phi Nguyen, Shafiq Joty, Steven C. H. Hoi, Richard Socher

Comments ICLR 2020

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

Junnan Li, Richard Socher, Steven C. H. Hoi

Journal ref International Conference on Learning Representations, 2020

Self-labelling via simultaneous clustering and representation learning

Yuki Markus Asano, Christian Rupprecht, Andrea Vedaldi

Comments Accepted paper at the International Conference on Learning Representations (ICLR) 2020

Decoupling Representation and Classifier for Long-Tailed Recognition

Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, Yannis Kalantidis

Journal ref Published as a conference paper at ICLR 2020

Strategies for Pre-training Graph Neural Networks

Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec

Comments Accepted as a spotlight to ICLR 2020

A critical analysis of self-supervision, or what we can learn from a single image

Yuki M. Asano, Christian Rupprecht, Andrea Vedaldi

Comments Accepted paper at the International Conference on Learning Representations (ICLR) 2020

Gradient $\ell_1$ Regularization for Quantization Robustness

Milad Alizadeh, Arash Behboodi, Mart van Baalen, Christos Louizos, Tijmen Blankevoort, Max Welling

Comments ICLR 2020

Reformer: The Efficient Transformer

Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya

Comments ICLR 2020

Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework

Zirui Wang, Jiateng Xie, Ruochen Xu, Yiming Yang, Graham Neubig, Jaime Carbonell

Comments Published as a conference paper at ICLR 2020. First two authors contributed equally. Source code is available at https://github.com/thespectrewithin/joint-align

Meta-Learning with Warped Gradient Descent

Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Francesco Visin, Hujun Yin, Raia Hadsell

Comments 28 pages, 13 figures, 3 tables. Published as a conference paper at ICLR 2020

VL-BERT: Pre-training of Generic Visual-Linguistic Representations

Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai

Comments Accepted by ICLR 2020

Few-shot Text Classification with Distributional Signatures

Yujia Bao, Menghua Wu, Shiyu Chang, Regina Barzilay

Comments ICLR 2020

Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions

Yao Qin, Nicholas Frosst, Sara Sabour, Colin Raffel, Garrison Cottrell, Geoffrey Hinton

Journal ref ICLR 2020

Demystifying Inter-Class Disentanglement

Aviv Gabbay, Yedid Hoshen

Comments ICLR 2020. Project page: http://www.vision.huji.ac.il/lord

Gradient-Based Neural DAG Learning

Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu, Simon Lacoste-Julien

Comments Appears in: Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020). 23 pages

Incorporating BERT into Neural Machine Translation

Jinhua Zhu, Yingce Xia, Lijun Wu, Di He, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu

Comments Accepted to ICLR-2020

Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings

Shweta Mahajan, Iryna Gurevych, Stefan Roth

Comments Published as a conference paper at ICLR 2020

Compositional Languages Emerge in a Neural Iterated Learning Model

Yi Ren, Shangmin Guo, Matthieu Labeau, Shay B. Cohen, Simon Kirby

Comments accepted by ICLR-2020

Journal ref ICLR-2020

Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems

Chris Reinke, Mayalen Etcheverry, Pierre-Yves Oudeyer

Comments 29 pages, 19 figure, ICLR 2020 conference paper, associated website: https://automated-discovery.github.io/

Scalable Model Compression by Entropy Penalized Reparameterization

Deniz Oktay, Johannes Ballé, Saurabh Singh, Abhinav Shrivastava

Comments Published in ICLR 2020

A Signal Propagation Perspective for Pruning Neural Networks at Initialization

Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, Philip H. S. Torr

Comments ICLR 2020

Don't Use Large Mini-Batches, Use Local SGD

Tao Lin, Sebastian U. Stich, Kumar Kshitij Patel, Martin Jaggi

Comments To appear in ICLR 2020

A closer look at the approximation capabilities of neural networks

Kai Fong Ernest Chong

Comments Published as a conference paper at ICLR 2020