ICLR - arXivDaily 期刊&会议

2010.02354 2021-03-24 cs.NE cs.AI cs.LG

The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings

Elliot Meyerson, Risto Miikkulainen

Comments Accepted for spotlight presentation as a conference paper at ICLR 2021. Main paper: 9 pages; with references: 12 pages; with appendix: 17 pages. Best viewed in color

2010.02347 2021-03-24 cs.LG stat.ML

Learning with Instance-Dependent Label Noise: A Sample Sieve Approach

Hao Cheng, Zhaowei Zhu, Xingyu Li, Yifei Gong, Xing Sun, Yang Liu

Comments ICLR 2021

2008.01352 2021-03-24 cs.LG cs.NE stat.ML

PDE-Driven Spatiotemporal Disentanglement

Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari

Journal ref The Ninth International Conference on Learning Representations, International Conference on Representation Learning, May 2021, Vienne, Austria

2007.12348 2021-03-24 cs.CV cs.LG

Unsupervised Discovery of 3D Physical Objects from Video

Yilun Du, Kevin Smith, Tomer Ulman, Joshua Tenenbaum, Jiajun Wu

Comments ICLR 2021; project webpage at http://yilundu.github.io/podnet

2006.12459 2021-03-24 cs.LG stat.ML

IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression

Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans

Comments Accepted as a conference paper at the Ninth International Conference on Learning Representations (ICLR) 2021

2006.04528 2021-03-24 cs.LG stat.ML

Evaluation of Similarity-based Explanations

Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui

Comments ICLR 2021

2006.03355 2021-03-24 q-bio.NC cs.LG

Prediction and Generalisation over Directed Actions by Grid Cells

Changmin Yu, Timothy E. J. Behrens, Neil Burgess

Comments In Proceedings of ICLR 2021

2103.12051 2021-03-23 cs.CV cs.AI cs.LG

SSD: A Unified Framework for Self-Supervised Outlier Detection

Vikash Sehwag, Mung Chiang, Prateek Mittal

Comments ICLR 2021

2103.11882 2021-03-23 cs.LG cs.PL cs.SE

Generating Adversarial Computer Programs using Optimized Obfuscations

Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shiyu Chang, Quanfu Fan, Gaoyuan Zhang, Una-May O'Reilly

Comments This work will be published at ICLR 2021

2103.11647 2021-03-23 cs.CL cs.AI

Prototypical Representation Learning for Relation Extraction

Ning Ding, Xiaobin Wang, Yao Fu, Guangwei Xu, Rui Wang, Pengjun Xie, Ying Shen, Fei Huang, Hai-Tao Zheng, Rui Zhang

Comments Accepted by ICLR 2021

2103.11318 2021-03-23 cs.LG cs.SE

Language-Agnostic Representation Learning of Source Code from Structure and Context

Daniel Zügner, Tobias Kirschstein, Michele Catasta, Jure Leskovec, Stephan Günnemann

Comments ICLR 2021

2103.11023 2021-03-23 stat.ML cs.LG

Individually Fair Ranking

Amanda Bower, Hamid Eftekhari, Mikhail Yurochkin, Yuekai Sun

Comments ICLR Camera-Ready Version

2103.02143 2021-03-23 cs.CL

Random Feature Attention

Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah A. Smith, Lingpeng Kong

Comments ICLR 2021

2102.08159 2021-03-23 cs.LG cs.MA

RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents

Wei Qiu, Xinrun Wang, Runsheng Yu, Xu He, Rundong Wang, Bo An, Svetlana Obraztsova, Zinovi Rabinovich

Comments ICLR 2021 submission version: https://openreview.net/forum?id=1EVb8XRBDNr

2102.05188 2021-03-23 cs.LG cs.CR

CaPC Learning: Confidential and Private Collaborative Learning

Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang

Comments Published as a conference paper at ICLR 2021

2012.04781 2021-03-23 cs.CV cs.LG eess.IV

You Only Need Adversarial Supervision for Semantic Image Synthesis

Vadim Sushko, Edgar Schönfeld, Dan Zhang, Juergen Gall, Bernt Schiele, Anna Khoreva

Comments Published at ICLR 2021 (Main Conference). Code repository: https://github.com/boschresearch/OASIS

2010.09515 2021-03-23 cs.LG cs.AI stat.ML

Improving Transformation Invariance in Contrastive Representation Learning

Adam Foster, Rattana Pukdee, Tom Rainforth

Comments Published as a conference paper at ICLR 2021

2010.03697 2021-03-23 cs.LG cs.AI cs.CV

A Critique of Self-Expressive Deep Subspace Clustering

Benjamin D. Haeffele, Chong You, René Vidal

Comments Published as a conference paper at the International Conference on Learning Representations (ICLR) 2021

2010.02329 2021-03-23 cs.CL cs.AI cs.LG

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective

Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

Comments Accepted to ICLR 2021. 23 pages, 9 tables, 3 figures

2009.08576 2021-03-23 cs.LG cs.CV cs.NE stat.ML

Pruning Neural Networks at Initialization: Why are We Missing the Mark?

Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin

Comments Published in ICLR 2021

2007.15960 2021-03-23 cs.CL

On Learning Universal Representations Across Languages

Xiangpeng Wei, Rongxiang Weng, Yue Hu, Luxi Xing, Heng Yu, Weihua Luo

Comments Accepted to ICLR 2021

2007.07375 2021-03-23 cs.LG cs.CV stat.ML

Concept Learners for Few-Shot Learning

Kaidi Cao, Maria Brbic, Jure Leskovec

Comments Published at ICLR 2021

2003.00152 2021-03-23 cs.LG cs.AI cs.NE stat.ML

Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs

Jonathan Frankle, David J. Schwab, Ari S. Morcos

Comments Published in ICLR 2021

1909.12057 2021-03-23 cs.LG stat.ML

B-Spline CNNs on Lie Groups

Erik J Bekkers

Comments Accepted for publication at ICLR 2020, code available at https://github.com/ebekkers/gsplinets

2103.10432 2021-03-22 q-bio.BM cs.CE cs.LG

MARS: Markov Molecular Sampling for Multi-objective Drug Discovery

Yutong Xie, Chence Shi, Hao Zhou, Yuwei Yang, Weinan Zhang, Yong Yu, Lei Li

Comments ICLR 2021

2101.08134 2021-03-22 cs.LG cs.AI cs.NE

Zero-Cost Proxies for Lightweight NAS

Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas D. Lane

Comments ICLR 2021

2010.02089 2021-03-22 cs.LG stat.ML

CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks

Jiaqi Ma, Bo Chang, Xuefei Zhang, Qiaozhu Mei

Comments ICLR 2021

2010.00977 2021-03-22 cs.CV stat.ML

Group Equivariant Stand-Alone Self-Attention For Vision

David W. Romero, Jean-Baptiste Cordonnier

Comments Proceedings of the 9th International Conference on Learning Representations (ICLR), 2021

Journal ref Proceedings of the International Conference on Learning Representations, 2021

2008.05659 2021-03-22 cs.CV

What Should Not Be Contrastive in Contrastive Learning

Tete Xiao, Xiaolong Wang, Alexei A. Efros, Trevor Darrell

Comments Published as a conference paper at ICLR 2021

2007.00232 2021-03-22 cs.LG cs.DC stat.ML

Linear Convergent Decentralized Optimization with Compression

Xiaorui Liu, Yao Li, Rongrong Wang, Jiliang Tang, Ming Yan

Comments ICLR 2021 (International Conference on Learning Representations)