ICLR

E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking

Yangtian Zhang, Huiyu Cai, Chence Shi, Bozitao Zhong, Jian Tang

Comments International Conference on Learning Representations (ICLR 2023)

An Additive Instance-Wise Approach to Multi-class Model Interpretation

Vy Vo, Van Nguyen, Trung Le, Quan Hung Tran, Gholamreza Haffari, Seyit Camtepe, Dinh Phung

Journal ref In The Eleventh International Conference on Learning Representations, 2023

Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss

Moritz Vandenhirtz, Laura Manduchi, Ričards Marcinkevičs, Julia E. Vogt

Comments Presented at the Domain Generalization Workshop (ICLR 2023)

Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models

Liam Fowl, Jonas Geiping, Steven Reich, Yuxin Wen, Wojtek Czaja, Micah Goldblum, Tom Goldstein

Comments First two authors contributed equally. Order chosen by coin flip. Published at ICLR 2023. Implementation available at github.com/JonasGeiping/breaching

Learning Diverse Options via InfoMax Termination Critic

Yuji Kanagawa, Tomoyuki Kaneko

Comments Rejected from ICLR 2022. See https://openreview.net/forum?id=UTTrevGchy for reviews

Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models

Guande He, Jianfei Chen, Jun Zhu

Comments ICLR 2023

Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling

Qidong Yang, Alex Hernandez-Garcia, Paula Harder, Venkatesh Ramesh, Prasanna Sattegeri, Daniela Szwarcman, Campbell D. Watson, David Rolnick

Comments Presented at the ICLR 2023 workshop on "Tackling Climate Change with Machine Learning"

Analogy-Forming Transformers for Few-Shot 3D Parsing

Nikolaos Gkanatsios, Mayank Singh, Zhaoyuan Fang, Shubham Tulsiani, Katerina Fragkiadaki

Comments ICLR 2023

PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm

Toygun Basaklar, Suat Gumussoy, Umit Y. Ogras

Comments 24 pages, 8 Figures, 9 Tables, Published as a conference paper at ICLR 2023, https://openreview.net/forum?id=zS9sRyaPFlJ

Group equivariant neural posterior estimation

Maximilian Dax, Stephen R. Green, Jonathan Gair, Michael Deistler, Bernhard Schölkopf, Jakob H. Macke

Comments 13+11 pages, 5+8 figures. [v2]: Minor updates to match published version, code available at https://github.com/dingo-gw/dingo

Journal ref ICLR 2022

Confidence-Based Feature Imputation for Graphs with Partially Known Features

Daeho Um, Jiwoong Park, Seulki Park, Jin Young Choi

Comments Accepted to ICLR 2023. 28 pages

DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion

Qitian Wu, Chenxiao Yang, Wentao Zhao, Yixuan He, David Wipf, Junchi Yan

Comments Published at ICLR 2023 as a spotlight presentation, the implementation code is available at https://github.com/qitianwu/DIFFormer

STaSy: Score-based Tabular data Synthesis

Jayoung Kim, Chaejeong Lee, Noseong Park

Comments 27 pages, Accepted by ICLR 2023 for spotlight presentation, Official code: https://github.com/JayoungKim408/STaSy

Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets

Hayeon Lee, Sohyun An, Minseon Kim, Sung Ju Hwang

Comments ICLR 2023 (Notable-top-25%)

On Representing Mixed-Integer Linear Programs by Graph Neural Networks

Ziang Chen, Jialin Liu, Xinshang Wang, Jianfeng Lu, Wotao Yin

Comments ICLR 2023

The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks

Blake Bordelon, Cengiz Pehlevan

Comments ICLR 2023 Camera Ready

On Representing Linear Programs by Graph Neural Networks

Ziang Chen, Jialin Liu, Xinshang Wang, Jianfeng Lu, Wotao Yin

Comments ICLR 2023 spotlight

Towards Open Temporal Graph Neural Networks

Kaituo Feng, Changsheng Li, Xiaolu Zhang, Jun Zhou

Comments ICLR 2023 Oral, code is available at: https://github.com/tulerfeng/OTGNet

Understanding Label Bias in Single Positive Multi-Label Learning

Julio Arroyo, Pietro Perona, Elijah Cole

Comments ICLR 2023, Tiny Papers Track

Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics

Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin

Comments ICLR 2023 TinyPapers

Machine learning-assisted close-set X-ray diffraction phase identification of transition metals

Maksim Zhdanov, Andrey Zhdanov

Comments Published at the ICLR 2023 Workshop on Machine Learning for Materials, 5 pages, 1 figure

Bayesian calibration of differentiable agent-based models

Arnau Quera-Bofarull, Ayush Chopra, Anisoara Calinescu, Michael Wooldridge, Joel Dyer

Comments Accepted for Oral Presentation at the AI4ABM Workshop at ICLR 2023

Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction

Daehee Park, Hobin Ryu, Yunseo Yang, Jegyeong Cho, Jiwon Kim, Kuk-Jin Yoon

Comments ICLR 2023

Exploring Semantic Variations in GAN Latent Spaces via Matrix Factorization

Andrey Palaev, Rustam A. Lukmanov, Adil Khan

Comments Accepted at ICLR 2023 Tiny Papers

An Extensible Multimodal Multi-task Object Dataset with Materials

Trevor Standley, Ruohan Gao, Dawn Chen, Jiajun Wu, Silvio Savarese

Comments ICLR 2023

Mitigating climate and health impact of small-scale kiln industry using multi-spectral classifier and deep learning

Usman Nazir, Murtaza Taj, Momin Uppal, Sara Khalid

Comments Tackling Climate Change with Machine Learning workshop at ICLR 2023

Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?

Jie Ren, Zhanpeng Zhou, Qirui Chen, Quanshi Zhang

Comments accepted by ICLR 2023

NORM: Knowledge Distillation via N-to-One Representation Matching

Xiaolong Liu, Lujun Li, Chao Li, Anbang Yao

Comments The paper of NORM is published at ICLR 2023. Code and models are available at https://github.com/OSVAI/NORM

DiGress: Discrete Denoising diffusion for graph generation

Clement Vignac, Igor Krawczuk, Antoine Siraudin, Bohan Wang, Volkan Cevher, Pascal Frossard

Comments 22 pages. Published as a conference paper at ICLR 2023

Journal ref International Conference on Learning Representations (ICLR 2023)

Faster federated optimization under second-order similarity

Ahmed Khaled, Chi Jin

Comments Published at ICLR 2023