ICLR

A weakly supervised framework for high-resolution crop yield forecasts

Dilli R. Paudel, Diego Marcos, Allard de Wit, Hendrik Boogaard, Ioannis N. Athanasiadis

Comments Appeared at the AI for Earth Sciences workshop at @ICLR2022, April 29, 2022. https://ai4earthscience.github.io/iclr-2022-workshop/

Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias

Frederic Koehler, Viraj Mehta, Chenghui Zhou, Andrej Risteski

Comments Accepted as a conference paper at ICLR 2022

A simple yet effective baseline for non-attributed graph classification

Chen Cai, Yusu Wang

Comments 13 pages. Shorter version appears at 2019 ICLR Workshop: Representation Learning on Graphs and Manifolds

Partial Product Aware Machine Learning on DNA-Encoded Libraries

Polina Binder, Meghan Lawler, LaShadric Grady, Neil Carlson, Sumudu Leelananda, Svetlana Belyanskaya, Joe Franklin, Nicolas Tilmans, Henri Palacci

Comments 8 pages, 5 figures; Published at the MLDD workshop, ICLR 2022

Neural Program Synthesis with Query

Di Huang, Rui Zhang, Xing Hu, Xishan Zhang, Pengwei Jin, Nan Li, Zidong Du, Qi Guo, Yunji Chen

Comments Accepted by ICLR 2022

REMuS-GNN: A Rotation-Equivariant Model for Simulating Continuum Dynamics

Mario Lino, Stati Fotiadis, Anil A. Bharath, Chris Cantwell

Comments Accepted at the ICLR 2022 Workshop on Geometrical and Topological Representation Learning

Discovering Latent Concepts Learned in BERT

Fahim Dalvi, Abdul Rafae Khan, Firoj Alam, Nadir Durrani, Jia Xu, Hassan Sajjad

Comments ICLR 2022

Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection

Wei Ji, Jingjing Li, Qi Bi, Chuan Guo, Jie Liu, Li Cheng

Comments This paper appeared at ICLR 2022

A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model

Jianwen Xie, Yaxuan Zhu, Jun Li, Ping Li

Comments 23 pages

Journal ref ICLR 2022

ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity

Ginger Delmas, Rafael Sampaio de Rezende, Gabriela Csurka, Diane Larlus

Comments Published in ICLR 2022

Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting

Shikuang Deng, Yuhang Li, Shanghang Zhang, Shi Gu

Comments Published as a conference paper at ICLR 2022

SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, Yuan Cao

Comments Published at ICLR 2022

R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning

Shengyao Lu, Bang Liu, Keith G. Mills, Shangling Jui, Di Niu

Comments ICLR 2022 Spotlight

EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits

Yikun Ban, Yuchen Yan, Arindam Banerjee, Jingrui He

Comments Published on ICLR 2022

Learning more skills through optimistic exploration

DJ Strouse, Kate Baumli, David Warde-Farley, Vlad Mnih, Steven Hansen

Comments Accepted at ICLR 2022 (spotlight)

Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning

Yatao Bian, Yu Rong, Tingyang Xu, Jiaxiang Wu, Andreas Krause, Junzhou Huang

Comments ICLR 2022

Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, Yin Cui

Comments ICLR Camera Ready

Journal ref ICLR 2022

RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation

Pingchuan Ma, Tao Du, Joshua B. Tenenbaum, Wojciech Matusik, Chuang Gan

Comments ICLR Oral. Project page: http://risp.csail.mit.edu

PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions

Zhaoqi Leng, Mingxing Tan, Chenxi Liu, Ekin Dogus Cubuk, Xiaojie Shi, Shuyang Cheng, Dragomir Anguelov

Comments Add ablation studies on COCO detection using RetinaNet (Section 8)

Journal ref International Conference on Learning Representations. 2021

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients

Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama

Comments ICLR 2022 camera-ready version

Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models

Tri Dao, Beidi Chen, Kaizhao Liang, Jiaming Yang, Zhao Song, Atri Rudra, Christopher Ré

Comments International Conference on Learning Representations (ICLR) 2022 spotlight

Towards Model Agnostic Federated Learning Using Knowledge Distillation

Andrei Afonin, Sai Praneeth Karimireddy

Comments Published at ICLR 2022

Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise

Xingyu Wang, Sewoong Oh, Chang-Han Rhee

Comments Proceedings of 2022 International Conference on Learning Representations. 157 pages (12 pages for the main paper and 145 pages for the supplementary materials)

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

Xuefeng Du, Zhaoning Wang, Mu Cai, Yixuan Li

Comments ICLR 2022

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

Elahe Arani, Fahad Sarfraz, Bahram Zonooz

Comments Published as a conference paper at ICLR 2022 (camera-ready version)

Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path

X. Y. Han, Vardan Papyan, David L. Donoho

Comments ICLR 2022 Outstanding Paper Prize & Oral. Appendix contains [A] empirical experiments, [B-D] proofs of theoretical results, and [E] survey of related works examining Neural Collapse

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

Yuan Yin, Vincent Le Guen, Jérémie Dona, Emmanuel de Bézenac, Ibrahim Ayed, Nicolas Thome, Patrick Gallinari

Comments Accepted at ICLR 2021 (Oral)

Journal ref J. Stat. Mech. (2021) 124012

ConceptDistil: Model-Agnostic Distillation of Concept Explanations

João Bento Sousa, Ricardo Moreira, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro

Comments ICLR 2022 PAIR2Struct Workshop

Pareto Set Learning for Neural Multi-objective Combinatorial Optimization

Xi Lin, Zhiyuan Yang, Qingfu Zhang

Comments Accepted by ICLR 2022, Final Camera-Ready Version

Symbolic Learning to Optimize: Towards Interpretability and Scalability

Wenqing Zheng, Tianlong Chen, Ting-Kuei Hu, Zhangyang Wang

Comments Published as a conference paper at ICLR 2022