ICLR

MARS: Meta-Learning as Score Matching in the Function Space

Krunoslav Lehman Pavasovic, Jonas Rothfuss, Andreas Krause

Comments In International Conference on Learning Representations (ICLR), 2023

The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers

Zonglin Li, Chong You, Srinadh Bhojanapalli, Daliang Li, Ankit Singh Rawat, Sashank J. Reddi, Ke Ye, Felix Chern, Felix Yu, Ruiqi Guo, Sanjiv Kumar

Comments A short version was presented at ICLR 2023. Previous title: Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers

Self-Distillation for Further Pre-training of Transformers

Seanie Lee, Minki Kang, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi

Comments ICLR 2023

MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning

Namyong Park, Ryan Rossi, Nesreen Ahmed, Christos Faloutsos

Comments ICLR 2023

Stochastic Multi-Person 3D Motion Forecasting

Sirui Xu, Yu-Xiong Wang, Liang-Yan Gui

Comments ICLR 2023 (Top 25% Paper); Project Page: https://sirui-xu.github.io/DuMMF

Stability of implicit neural networks for long-term forecasting in dynamical systems

Leon Migus, Julien Salomon, Patrick Gallinari

Comments ICLR 2023 Workshop on Physics for Machine Learning

Improve State-Level Wheat Yield Forecasts in Kazakhstan on GEOGLAM's EO Data by Leveraging A Simple Spatial-Aware Technique

Anh Nhat Nhu, Ritvik Sahajpal, Christina Justice, Inbal Becker-Reshef

Comments Accepted to (ICLR) 2023 Workshop on Machine Learning for Remote Sensing

Journal ref International Conference on Learning Representation (ICLR), First Workshop on Machine Learning for Remote Sensing, 2023

Differentially Private Adaptive Optimization with Delayed Preconditioners

Tian Li, Manzil Zaheer, Ken Ziyu Liu, Sashank J. Reddi, H. Brendan McMahan, Virginia Smith

Comments Accepted by ICLR 2023

Explicit Knowledge Transfer for Weakly-Supervised Code Generation

Zhangir Azerbayev, Ansong Ni, Hailey Schoelkopf, Dragomir Radev

Comments Updated on Jun 7. 2023 with ICLR workshop header

Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning

Jian Hu, Siyang Jiang, Seth Austin Harding, Haibin Wu, Shih-wei Liao

Comments Accepted by ICLR BlogTrack 2023

Policy-Based Self-Competition for Planning Problems

Jonathan Pirnay, Quirin Göttl, Jakob Burger, Dominik Gerhard Grimm

Comments 24 pages, 5 figures

Journal ref The Eleventh International Conference on Learning Representations, 2023

Deep Learning From Crowdsourced Labels: Coupled Cross-entropy Minimization, Identifiability, and Regularization

Shahana Ibrahim, Tri Nguyen, Xiao Fu

Comments 39 pages, 5 figures, ICLR 2023

Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors

Zeyu Tang, Yatong Chen, Yang Liu, Kun Zhang

Journal ref The 11th International Conference on Learning Representations (ICLR 2023)

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

Yoonho Lee, Annie S. Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn

Comments ICLR 2023

Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners

Seonghyeon Ye, Doyoung Kim, Joel Jang, Joongbo Shin, Minjoon Seo

Comments ICLR 2023

Growing Efficient Deep Networks by Structured Continuous Sparsification

Xin Yuan, Pedro Savarese, Michael Maire

Comments Published as a conference paper at ICLR 2021

Label-Free Concept Bottleneck Models

Tuomas Oikarinen, Subhro Das, Lam M. Nguyen, Tsui-Wei Weng

Comments Published at ICLR 2023. New v2(5 June 2023): added crowdsourced human study in Appendix B

Stochastic Differentially Private and Fair Learning

Andrew Lowy, Devansh Gupta, Meisam Razaviyayn

Comments ICLR 2023

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Nan Ding, Keran Rong, Hassan Akbari, Gaurav Mishra, Linting Xue, Ashish Thapliyal, James Bradbury, Weicheng Kuo, Mojtaba Seyedhosseini, Chao Jia, Burcu Karagol Ayan, Carlos Riquelme, Andreas Steiner, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut

Comments ICLR 2023 (Notable-top-5%)

LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval

Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang

Comments Appeared at ICLR 2023

CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks

Tuomas Oikarinen, Tsui-Wei Weng

Comments Published in ICLR 2023 Conference (Spotlight). New v5(5 June 2023) - Added crowdsourced user study in Appendix B, not included in ICLR publication

Beyond Negativity: Re-Analysis and Follow-Up Experiments on Hope Speech Detection

Neemesh Yadav, Mohammad Aflah Khan, Diksha Sethi, Raghav Sahni

Comments Published as a Tiny Paper at ICLR 2023, 7 Pages

Semi-supervised Community Detection via Structural Similarity Metrics

Yicong Jiang, Tracy Ke

Comments 9 pages, 8 figures, accepted by the 11th International Conference on Learning Representations (ICLR 2023)

Pseudo Labels for Single Positive Multi-Label Learning

Julio Arroyo

Comments ICLR 2023, Tiny Papers Track

TopEx: Topic-based Explanations for Model Comparison

Shreya Havaldar, Adam Stein, Eric Wong, Lyle Ungar

Comments Accepted to ICLR 2023, Tiny Papers Track

Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization

Zonghan Yang, Xiaoyuan Yi, Peng Li, Yang Liu, Xing Xie

Comments Accepted at ICLR 2023

Fast Nonlinear Vector Quantile Regression

Aviv A. Rosenberg, Sanketh Vedula, Yaniv Romano, Alex M. Bronstein

Comments 35 pages, 15 figures, code: https://github.com/vistalab-technion/vqr

Journal ref The Eleventh International Conference on Learning Representations (ICLR 2023)

Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding

Tianyang Hu, Zhili Liu, Fengwei Zhou, Wenjia Wang, Weiran Huang

Comments Accepted by ICLR 2023

Improving Protein-peptide Interface Predictions in the Low Data Regime

Justin Diamond, Markus Lill

Comments 5 pages, 5 figures, ICLR Machine Learning in Drug Discovery Accepted paper

Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries

Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, Tom Goldstein

Comments Code is available at https://github.com/YuxinWenRick/canary-in-a-coalmine, published as a conference paper at ICLR 2023