ICLR

Debiasing Concept-based Explanations with Causal Analysis

Mohammad Taha Bahadori, David E. Heckerman

Comments Accepted in ICLR 2021

Evening the Score: Targeting SARS-CoV-2 Protease Inhibition in Graph Generative Models for Therapeutic Candidates

Jenna Bilbrey, Logan Ward, Sutanay Choudhury, Neeraj Kumar, Ganesh Sivaraman

Comments arXiv admin note: substantial text overlap with arXiv:2102.04977

Journal ref Published at ICLR 2021 Workshop on Machine Learning for Preventing and Combating Pandemics

Data-driven Weight Initialization with Sylvester Solvers

Debasmit Das, Yash Bhalgat, Fatih Porikli

Comments Practical Machine Learning for Developing Countries Workshop, International Conference on Learning Representations, 2021

Simple Transparent Adversarial Examples

Jaydeep Borkar, Pin-Yu Chen

Comments 14 pages, 9 figures, Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems

VTNet: Visual Transformer Network for Object Goal Navigation

Heming Du, Xin Yu, Liang Zheng

Comments accepted paper at ICLR 2021

Data-Efficient Reinforcement Learning with Self-Predictive Representations

Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, Philip Bachman

Comments The first two authors contributed equally to this work. v4 includes new ablations and reformatting for ICLR camera ready

Emergent Coordination Through Competition

Siqi Liu, Guy Lever, Josh Merel, Saran Tunyasuvunakool, Nicolas Heess, Thore Graepel

Journal ref ICLR (2019)

Fast and Slow Learning of Recurrent Independent Mechanisms

Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Schölkopf, Yoshua Bengio

Comments Accepted at ICLR'21

Learning a Latent Simplex in Input-Sparsity Time

Ainesh Bakshi, Chiranjib Bhattacharyya, Ravi Kannan, David P. Woodruff, Samson Zhou

Comments ICLR 2021

Undistillable: Making A Nasty Teacher That CANNOT teach students

Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Comments ICLR 2021(Spotlight). Code is available at https://github.com/VITA-Group/Nasty-Teacher

Journal ref ICLR 2021

Learning from Protein Structure with Geometric Vector Perceptrons

Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael J. L. Townshend, Ron Dror

Comments Presented at ICLR 2021

High-Robustness, Low-Transferability Fingerprinting of Neural Networks

Siyue Wang, Xiao Wang, Pin-Yu Chen, Pu Zhao, Xue Lin

Comments ICLR 2021 Workshop on Security and Safety in Machine Learning Systems

Hierarchical Variational Auto-Encoding for Unsupervised Domain Generalization

Xudong Sun, Florian Buettner

Comments Presented at ICLR 2021 RobustML Workshop

Measuring Adversarial Robustness using a Voronoi-Epsilon Adversary

Hyeongji Kim, Pekka Parviainen, Ketil Malde

Comments 10 pages. Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems. Some definitions (names) are changed from the previous versions. Some sections are also removed. This paper supersedes the paper "Finding a human-like classifier". (https://openreview.net/forum?id=BJeGFs9FsH)

Exploring the Similarity of Representations in Model-Agnostic Meta-Learning

Thomas Goerttler, Klaus Obermayer

Comments Learning to Learn workshop at ICLR 2021

Global Convergence of Three-layer Neural Networks in the Mean Field Regime

Huy Tuan Pham, Phan-Minh Nguyen

Comments Appear in ICLR 2021. This is the conference version of arXiv:2001.11443 (which contains treatment of the multilayer neural nets and their global convergence)

Language Acquisition is Embodied, Interactive, Emotive: a Research Proposal

Casey Kennington

Comments 6 pages, ICLR 2021 Embodied Multimodal Learning Workshop

Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

Tsung-Wei Ke, Jyh-Jing Hwang, Stella X. Yu

Comments In ICLR 2021. Webpage & Code: https://twke18.github.io/projects/spml.html

FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Michael Kamp, Qi Dou

Comments Accepted at ICLR 2021

Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks

Keming Zhang, Joshua S. Bloom

Comments Accepted to MNRAS. Extended abstract accepted to NeurIPS 2020: Machine Learning for the Physical Sciences. Initially appeared in ICLR 2020: Fundamental Science in the Era of AI. Open source implementation at https://github.com/kmzzhang/periodicnetwork. 8 pages, 4 figures

Auxiliary Learning by Implicit Differentiation

Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, Ethan Fetaya

Comments Published at ICLR 2021

Scaffolding Simulations with Deep Learning for High-dimensional Deconvolution

Anders Andreassen, Patrick T. Komiske, Eric M. Metodiev, Benjamin Nachman, Adi Suresh, Jesse Thaler

Comments 6 pages, 1 figure, 1 table

Journal ref ICLR simDL workshop 2021 (https://simdl.github.io/files/12.pdf)

Do Concept Bottleneck Models Learn as Intended?

Andrei Margeloiu, Matthew Ashman, Umang Bhatt, Yanzhi Chen, Mateja Jamnik, Adrian Weller

Comments Accepted at ICLR 2021 Workshop on Responsible AI

Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception

Pablo Lanillos, Marcel van Gerven

Comments Accepted at ICLR 2021 Brain2AI workshop

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching

Jonas Geiping, Liam Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein

Comments First two authors contributed equally. Last two authors contributed equally. 21 pages, 11 figures. Published at ICLR 2021

Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering

Calypso Herrera, Florian Krach, Josef Teichmann

Journal ref International Conference on Learning Representations (2021)

Transitioning from Real to Synthetic data: Quantifying the bias in model

Aman Gupta, Deepak Bhatt, Anubha Pandey

Comments Accepted at Synthetic Data Generation Workshop at ICLR 2021 https://sdg-quality-privacy-bias.github.io/papers/

Fine-Grained $ε$-Margin Closed-Form Stabilization of Parametric Hawkes Processes

Rafael Lima

Comments Presented as a RobustML workshop paper at ICLR 2021

HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks

Ziyao Li, Shuwen Yang, Guojie Song, Lingsheng Cai

Comments in ICLR-2021 (poster)

Layer-adaptive sparsity for the Magnitude-based Pruning

Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin

Comments ICLR 2021. Changed title (previous ver: A deeper look at the layerwise sparsity of magnitude-based pruning)