ICLR

Re-parameterizing Your Optimizers rather than Architectures

Xiaohan Ding, Honghao Chen, Xiangyu Zhang, Kaiqi Huang, Jungong Han, Guiguang Ding

Comments ICLR 2023

Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel

Ryuichi Kanoh, Mahito Sugiyama

Comments Accepted to ICLR 2023

Diagnosing and Rectifying Vision Models using Language

Yuhui Zhang, Jeff Z. HaoChen, Shih-Cheng Huang, Kuan-Chieh Wang, James Zou, Serena Yeung

Comments Published at ICLR 2023

The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition

Jun Cen, Di Luan, Shiwei Zhang, Yixuan Pei, Yingya Zhang, Deli Zhao, Shaojie Shen, Qifeng Chen

Comments Accepted by ICLR 2023

Exploring Active 3D Object Detection from a Generalization Perspective

Yadan Luo, Zhuoxiao Chen, Zijian Wang, Xin Yu, Zi Huang, Mahsa Baktashmotlagh

Comments To appear in ICLR 2023

Anti-Symmetric DGN: a stable architecture for Deep Graph Networks

Alessio Gravina, Davide Bacciu, Claudio Gallicchio

Comments Accepted at ICLR 2023 (https://openreview.net/forum?id=J3Y7cgZOOS)

A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps

Kiarash Jamali, Dari Kimanius, Sjors H. W. Scheres

Comments The Eleventh International Conference on Learning Representations

Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution

Chao Chen, Haoyu Geng, Gang Zeng, Zhaobing Han, Hua Chai, Xiaokang Yang, Junchi Yan

Comments Published in ICLR 2023

Information-Theoretic Diffusion

Xianghao Kong, Rob Brekelmans, Greg Ver Steeg

Comments 26 pages, 7 figures, International Conference on Learning Representations (ICLR), 2023. Code is at http://github.com/kxh001/ITdiffusion and http://github.com/gregversteeg/InfoDiffusionSimple

Population-size-Aware Policy Optimization for Mean-Field Games

Pengdeng Li, Xinrun Wang, Shuxin Li, Hau Chan, Bo An

Comments Accepted to International Conference on Learning Representations (ICLR 2023)

Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs

Yu Duan, Zhongfan Jia, Qian Li, Yi Zhong, Kaisheng Ma

Comments Published as a conference paper at ICLR 2023

PatchDCT: Patch Refinement for High Quality Instance Segmentation

Qinrou Wen, Jirui Yang, Xue Yang, Kewei Liang

Comments 15 pages, 7 figures, 13 tables, accepted by ICLR 2023, the source code is available at https://github.com/olivia-w12/PatchDCT

A Non-monotonic Self-terminating Language Model

Eugene Choi, Kyunghyun Cho, Cheolhyoung Lee

Comments Published as a conference paper at ICLR 2023

Contrastive Learning for Unsupervised Domain Adaptation of Time Series

Yilmazcan Ozyurt, Stefan Feuerriegel, Ce Zhang

Comments Published as a conference paper at ICLR 2023

Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting

Amin Shabani, Amir Abdi, Lili Meng, Tristan Sylvain

Comments ICLR 2023

Variance-Aware Sparse Linear Bandits

Yan Dai, Ruosong Wang, Simon S. Du

Comments Accepted to ICLR 2023

Learning What and Where: Disentangling Location and Identity Tracking Without Supervision

Manuel Traub, Sebastian Otte, Tobias Menge, Matthias Karlbauer, Jannik Thümmel, Martin V. Butz

Comments Accepted at ICLR 2023

Understanding Why Generalized Reweighting Does Not Improve Over ERM

Runtian Zhai, Chen Dan, Zico Kolter, Pradeep Ravikumar

Comments ICLR 2023. 40 pages, 3 figures

AIM: Adapting Image Models for Efficient Video Action Recognition

Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, Mu Li

Comments Accepted to ICLR 2023. Project webpage is at https://adapt-image-models.github.io/

DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models

Tiange Xiang, Mahmut Yurt, Ali B Syed, Kawin Setsompop, Akshay Chaudhari

Comments To appear in ICLR 2023

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning

Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, Dacheng Tao

Comments ICLR 2023 (Notable-top-25%)

Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks

Shuai Zhang, Meng Wang, Pin-Yu Chen, Sijia Liu, Songtao Lu, Miao Liu

Journal ref The Eleventh International Conference on Learning Representations, 2023

Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks

Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann

Comments Accepted at ICLR 2021 (https://openreview.net/forum?id=ULQdiUTHe3y). Uploaded to arxiv to fix Google Scholar indexing

Hierarchical Sliced Wasserstein Distance

Khai Nguyen, Tongzheng Ren, Huy Nguyen, Litu Rout, Tan Nguyen, Nhat Ho

Comments Accepted to ICLR 2023, 29 pages, 8 figures, 3 tables,

PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs

James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras

Comments Accepted at ICLR 2023. Code available at: https://github.com/james-oldfield/PandA

The KFIoU Loss for Rotated Object Detection

Xue Yang, Yue Zhou, Gefan Zhang, Jirui Yang, Wentao Wang, Junchi Yan, Xiaopeng Zhang, Qi Tian

Comments 18 pages, 6 figures, 8 tables, accepted by ICLR 2023, TensorFlow code: https://github.com/yangxue0827/RotationDetection, PyTorch code: https://github.com/open-mmlab/mmrotate, Jittor code: https://github.com/Jittor/JDet

Real-Time Image Demoireing on Mobile Devices

Yuxin Zhang, Mingbao Lin, Xunchao Li, Han Liu, Guozhi Wang, Fei Chao, Shuai Ren, Yafei Wen, Xiaoxin Chen, Rongrong Ji

Comments To appear in the eleventh International Conference on Learning Representations (ICLR 2023)

Representational dissimilarity metric spaces for stochastic neural networks

Lyndon R. Duong, Jingyang Zhou, Josue Nassar, Jules Berman, Jeroen Olieslagers, Alex H. Williams

Comments Published as a conference paper at ICLR 2023

Journal ref International Conference on Learning Representations 2023

Bidirectional Language Models Are Also Few-shot Learners

Ajay Patel, Bryan Li, Mohammad Sadegh Rasooli, Noah Constant, Colin Raffel, Chris Callison-Burch

Comments To appear at ICLR 2023

Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval

Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, Ge Yu

Comments Accepted by ICLR 2023