ICLR

Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting

Xiangyu Qi, Jifeng Zhu, Chulin Xie, Yong Yang

Comments 6 pages, 3 figures, ICLR 2021 Workshop on Security and Safety in Machine Learning System

Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks

Ingmar Schubert, Ozgur S. Oguz, Marc Toussaint

Comments Published as a conference paper at ICLR 2021

Journal ref ICLR 2021 - 9th International Conference on Learning Representations

You Only Write Thrice: Creating Documents, Computational Notebooks and Presentations From a Single Source

Kacper Sokol, Peter Flach

Comments Published at Rethinking ML Papers -- ICLR 2021 Workshop. OpenReview: https://openreview.net/forum?id=i4zpuNRiU4G Exhibit: https://so-cool.github.io/you-only-write-thrice/

Diverse Video Generation using a Gaussian Process Trigger

Gaurav Shrivastava, Abhinav Shrivastava

Comments International Conference on Learning Representations, 2021

Long-tail learning via logit adjustment

Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, Sanjiv Kumar

Comments Published as a conference paper in ICLR 2021

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models

Cassidy Laidlaw, Sahil Singla, Soheil Feizi

Comments Published in ICLR 2021. Code and data are available at https://github.com/cassidylaidlaw/perceptual-advex

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

Thomas Miconi, Aditya Rawal, Jeff Clune, Kenneth O. Stanley

Comments Presented at the 7th International Conference on Learning Representations (ICLR 2019)

Journal ref 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019

Unsupervised Audiovisual Synthesis via Exemplar Autoencoders

Kangle Deng, Aayush Bansal, Deva Ramanan

Comments ICLR 2021; Project page -- https://www.cs.cmu.edu/~exemplar-ae/

GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images

Sungmin Cha, Taeeon Park, Byeongjoon Kim, Jongduk Baek, Taesup Moon

Comments ICLR 2021 camera ready version

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets

Hayeon Lee, Eunyoung Hyung, Sung Ju Hwang

Comments ICLR 2021

FedMix: Approximation of Mixup under Mean Augmented Federated Learning

Tehrim Yoon, Sumin Shin, Sung Ju Hwang, Eunho Yang

Journal ref ICLR 2021

Ladder Polynomial Neural Networks

Li-Ping Liu, Ruiyuan Gu, Xiaozhe Hu

Comments The work has been first submitted to ICLR 2019 (submission link). Unfortunately the contribution was not sufficiently appreciated by reviewers

Accurate Learning of Graph Representations with Graph Multiset Pooling

Jinheon Baek, Minki Kang, Sung Ju Hwang

Comments ICLR 2021

Generalized Multimodal ELBO

Thomas M. Sutter, Imant Daunhawer, Julia E. Vogt

Comments 2021 ICLR

Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation

Jungo Kasai, Nikolaos Pappas, Hao Peng, James Cross, Noah A. Smith

Comments ICLR 2021 Final Version

Taming GANs with Lookahead-Minmax

Tatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich, Francois Fleuret, Martin Jaggi

Journal ref ICLR 2021

MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders

Daniel Dimanov, Emili Balaguer-Ballester, Colin Singleton, Shahin Rostami

Comments Published as a Poster paper in ICLR 2021 Neural Architecture Search workshop

Dependency Structure Misspecification in Multi-Source Weak Supervision Models

Salva Rühling Cachay, Benedikt Boecking, Artur Dubrawski

Comments Oral presentation at the Workshop on Weakly Supervised Learning at ICLR 2021

Learning to Represent Action Values as a Hypergraph on the Action Vertices

Arash Tavakoli, Mehdi Fatemi, Petar Kormushev

Comments ICLR 2021, code: https://github.com/atavakol/action-hypergraph-networks

GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding

Chenhui Deng, Zhiqiang Zhao, Yongyu Wang, Zhiru Zhang, Zhuo Feng

Comments Published as a conference paper at ICLR 2020

Journal ref International Conference on Learning Representations, ICLR 2020

Zero-Shot Federated Learning with New Classes for Audio Classification

Gautham Krishna Gudur, Satheesh K. Perepu

Comments Accepted at Interspeech 2021. Also accepted at the Distributed and Private Machine Learning (DPML) and Hardware Aware Efficient Training (HAET) workshops at ICLR 2021

Learning Mesh-Based Simulation with Graph Networks

Tobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, Peter W. Battaglia

Journal ref International Conference on Learning Representations (ICLR), 2021

Learning-based Support Estimation in Sublinear Time

Talya Eden, Piotr Indyk, Shyam Narayanan, Ronitt Rubinfeld, Sandeep Silwal, Tal Wagner

Comments 17 pages. Published as a conference paper in ICLR 2021

Reset-Free Lifelong Learning with Skill-Space Planning

Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch

Comments In the proceedings of the 7th International Conference on Learning Representations (ICLR), Virtual, April 2021

Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers

Chace Ashcraft, Kiran Karra

Comments 4 pages, 1 figure, Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems

Low-Rank Projections of GCNs Laplacian

Nathan Grinsztajn, Philippe Preux, Edouard Oyallon

Journal ref ICLR 2021 Workshop GTRL, 2021, Online, France

Transformation Importance with Applications to Cosmology

Chandan Singh, Wooseok Ha, Francois Lanusse, Vanessa Boehm, Jia Liu, Bin Yu

Comments Published in ICLR 2020 Workshop on Fundamental Science in the era of AI

Expected Tight Bounds for Robust Training

Salman Alsubaihi, Adel Bibi, Modar Alfadly, Abdullah Hamdi, Bernard Ghanem

Comments Presented as a RobustML workshop paper at ICLR 2021

Fantastic Four: Differentiable Bounds on Singular Values of Convolution Layers

Sahil Singla, Soheil Feizi

Comments Accepted at ICLR, 2021

DDPNOpt: Differential Dynamic Programming Neural Optimizer

Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou

Comments Accepted in International Conference on Learning Representations (ICLR) 2021 as Spotlight

Journal ref 10th International Conference on Learning Representations (ICLR 2021)