ICLR

Measuring Forgetting of Memorized Training Examples

Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Chiyuan Zhang

Comments Appeared at ICLR '23, 22 pages, 12 figures

Toeplitz Neural Network for Sequence Modeling

Zhen Qin, Xiaodong Han, Weixuan Sun, Bowen He, Dong Li, Dongxu Li, Yuchao Dai, Lingpeng Kong, Yiran Zhong

Comments Accepted to ICLR 2023 Spotlight. Yiran Zhong is the corresponding author. 15B pretrained LLM with TNN will be released at https://github.com/OpenNLPLab/Tnn soon

AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Scheme

Yungi Jeong, Eunseok Yang, Jung Hyun Ryu, Imseong Park, Myungjoo Kang

Comments 11 pages, Presented at ICLR 2023 workshop on Machine Learning for IoT

Multimodal Federated Learning via Contrastive Representation Ensemble

Qiying Yu, Yang Liu, Yimu Wang, Ke Xu, Jingjing Liu

Comments ICLR 2023, update

Provable Defense Against Geometric Transformations

Rem Yang, Jacob Laurel, Sasa Misailovic, Gagandeep Singh

Comments ICLR 2023 notable-top-25%

In-situ Anomaly Detection in Additive Manufacturing with Graph Neural Networks

Sebastian Larsen, Paul A. Hooper

Comments 5 pages, 3 figures, published in ICLR 2023 workshop on machine learning for materials (ML4Materials)

Widespread Increases in Future Wildfire Risk to Global Forest Carbon Offset Projects Revealed by Explainable AI

Tristan Ballard, Matthew Cooper, Chris Lowrie, Gopal Erinjippurath

Comments 6 pages, 5 figures. Published in ICLR 2023 Workshop: Tackling Climate Change with Machine Learning

Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration

Chentian Jiang, Nan Rosemary Ke, Hado van Hasselt

Comments In proceedings of the Reincarnating Reinforcement Learning (RRL) Workshop at ICLR 2023 and the Neuro-Symbolic AI for Agent and Multi-Agent Systems (NeSyMAS) Workshop at AAMAS 2023

Learning Topology-Preserving Data Representations

Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii, Nikita Balabin, Evgeny Burnaev, Serguei Barannikov

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

Unbiased Supervised Contrastive Learning

Carlo Alberto Barbano, Benoit Dufumier, Enzo Tartaglione, Marco Grangetto, Pietro Gori

Comments Accepted at ICLR 2023 (v3); Fix typo in Eq.19 (v4)

CrAM: A Compression-Aware Minimizer

Alexandra Peste, Adrian Vladu, Eldar Kurtic, Christoph H. Lampert, Dan Alistarh

Comments Accepted to ICLR 2023

Rethinking Graph Lottery Tickets: Graph Sparsity Matters

Bo Hui, Da Yan, Xiaolong Ma, Wei-Shinn Ku

Comments ICLR 2023

An Exploration of Conditioning Methods in Graph Neural Networks

Yeskendir Koishekenov, Erik J. Bekkers

Journal ref ICLR 2023 - Machine Learning for Drug Discovery workshop

SLTUNET: A Simple Unified Model for Sign Language Translation

Biao Zhang, Mathias Müller, Rico Sennrich

Comments ICLR 2023

NELoRa-Bench: A Benchmark for Neural-enhanced LoRa Demodulation

Jialuo Du, Yidong Ren, Mi Zhang, Yunhao Liu, Zhichao Cao

Comments Accepted by International Conference on Learning Representations (ICLR'23) Workshop on Machine Learning for IoT

Accelerating Neural Self-Improvement via Bootstrapping

Kazuki Irie, Jürgen Schmidhuber

Comments Presented at ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models, https://openreview.net/forum?id=SDwUYcyOCyP

From Local to Global: Navigating Linguistic Diversity in the African Context

Rashmi Margani, Nelson Ndugu

Comments ICLR 2023 NLP Workshop

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard A. Moser, Sergei Pereverzyev, Sepp Hochreiter, Werner Zellinger

Comments Oral talk (notable-top-5%) at International Conference On Learning Representations (ICLR), 2023

Journal ref International Conference On Learning Representations (ICLR), https://openreview.net/forum?id=M95oDwJXayG, 2023

DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning

Wenqiang Sun, Sen Li, Yuchang Sun, Jun Zhang

Comments Accepted by Backdoor Attacks and Defenses in Machine Learning (BANDS) Workshop at ICLR 2023

Learning Controllable Adaptive Simulation for Multi-resolution Physics

Tailin Wu, Takashi Maruyama, Qingqing Zhao, Gordon Wetzstein, Jure Leskovec

Comments ICLR 2023, notable top-25% (spotlight), 19 pages, 9 figures

Bird Distribution Modelling using Remote Sensing and Citizen Science data

Mélisande Teng, Amna Elmustafa, Benjamin Akera, Hugo Larochelle, David Rolnick

Journal ref Tackling Climate Change with Machine Learning Workshop, 11th International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda

Deep Ensembles to Improve Uncertainty Quantification of Statistical Downscaling Models under Climate Change Conditions

Jose González-Abad, Jorge Baño-Medina

Comments Accepted at the ICLR 2023 Tackling Climate Change with Machine Learning Workshop

Revisiting Robustness in Graph Machine Learning

Lukas Gosch, Daniel Sturm, Simon Geisler, Stephan Günnemann

Comments Published as a conference paper at ICLR 2023. Preliminary version accepted as an oral at the NeurIPS 2022 TSRML workshop and at the NeurIPS 2022 ML safety workshop

ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond

Xiaojun Guo, Yifei Wang, Tianqi Du, Yisen Wang

Comments ICLR 2023

Noise Injection Node Regularization for Robust Learning

Noam Levi, Itay M. Bloch, Marat Freytsis, Tomer Volansky

Comments 16 pages, 9 figures

Journal ref Proceedings of the International Conference on Learning Representations (ICLR), 2023

Noise Injection as a Probe of Deep Learning Dynamics

Noam Levi, Itay Bloch, Marat Freytsis, Tomer Volansky

Comments 11 pages, 3 figures

Journal ref Physics4ML Workshop, Proceedings of the International Conference on Learning Representations (ICLR), 2023

Graph Neural Networks for Link Prediction with Subgraph Sketching

Benjamin Paul Chamberlain, Sergey Shirobokov, Emanuele Rossi, Fabrizio Frasca, Thomas Markovich, Nils Hammerla, Michael M. Bronstein, Max Hansmire

Comments 29 pages, 19 figures, 6 appendices

Journal ref The Eleventh International Conference on Learning Representations 2023 (oral - top 5%)

Extremely Simple Activation Shaping for Out-of-Distribution Detection

Andrija Djurisic, Nebojsa Bozanic, Arjun Ashok, Rosanne Liu

Comments Accepted paper at ICLR 2023. 22 pages (9 main + appendix), 9 figures

What Do Self-Supervised Vision Transformers Learn?

Namuk Park, Wonjae Kim, Byeongho Heo, Taekyung Kim, Sangdoo Yun

Comments ICLR 2023

ISAAC Newton: Input-based Approximate Curvature for Newton's Method

Felix Petersen, Tobias Sutter, Christian Borgelt, Dongsung Huh, Hilde Kuehne, Yuekai Sun, Oliver Deussen

Comments Published at ICLR 2023, Code @ https://github.com/Felix-Petersen/isaac, Video @ https://youtu.be/7RKRX-MdwqM