NeurIPS

When and What to Ask Through World States and Text Instructions: IGLU NLP Challenge Solution

Zhengxiang Shi, Jerome Ramos, To Eun Kim, Xi Wang, Hossein A. Rahmani, Aldo Lipani

Comments The work won NIPS 2022 IGLU Competition Research Prize. The first two authors contribute equally. arXiv admin note: substantial text overlap with arXiv:2204.08373

Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Ngai-Man Cheung

Comments The Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022), 14 pages

Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence

Thomas M. Sutter, Imant Daunhawer, Julia E. Vogt

Comments Accepted at NeurIPS 2020, camera-ready version

Journal ref 34th Conference on Neural Information Processing Systems (NeurIPS 2020)

Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks

Stephen Casper, Kaivalya Hariharan, Dylan Hadfield-Menell

Comments Best paper award at the NeurIPS 2022 ML Safety Workshop -- https://neurips2022.mlsafety.org/

FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings

Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Teleńczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux

Comments Accepted to NeurIPS, Datasets and Benchmarks Track, this version fixes typos in the datasets' table and the appendix

PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning

Hanhan Zhou, Tian Lan, Vaneet Aggarwal

Comments accepted at NeurIPS 2022

Journal ref Advances in Neural Information Processing Systems 35 (2022): 15757-15769

Manifold Topology Divergence: a Framework for Comparing Data Manifolds

Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov, Ekaterina Trimbach, Alexander Korotin, Alexander Filippov, Evgeny Burnaev

Journal ref 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare

Shengpu Tang, Maggie Makar, Michael W. Sjoding, Finale Doshi-Velez, Jenna Wiens

Comments 30 pages, 18 figures, 2 tables. NeurIPS 2022. Code available at https://github.com/MLD3/OfflineRL_FactoredActions

Convergence for score-based generative modeling with polynomial complexity

Holden Lee, Jianfeng Lu, Yixin Tan

Comments 43 pages

Journal ref Advances in Neural Information Processing Systems 35 (2022), 22870--22882

On the use of Deep Generative Models for Perfect Prognosis Climate Downscaling

Jose González-Abad, Jorge Baño-Medina, Ignacio Heredia Cachá

Comments Accepted at the NeurIPS 2021 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

Learning Debiased Classifier with Biased Committee

Nayeong Kim, Sehyun Hwang, Sungsoo Ahn, Jaesik Park, Suha Kwak

Comments Conference on Neural Information Processing Systems (NeurIPS), New Orleans, 2022

Robustness of Graph Neural Networks at Scale

Simon Geisler, Tobias Schmidt, Hakan Şirin, Daniel Zügner, Aleksandar Bojchevski, Stephan Günnemann

Comments 39 pages, 22 figures, 17 tables NeurIPS 2021

Doubly robust Thompson sampling for linear payoffs

Wonyoung Kim, Gi-soo Kim, Myunghee Cho Paik

Comments Accepted for NeurIPS 2021 (Spotlight)

Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning

Liangyu Zhang, Yang Peng, Wenhao Yang, Zhihua Zhang

Comments Shorter version accepted at NeurIPS 2022

Redundant representations help generalization in wide neural networks

Diego Doimo, Aldo Glielmo, Sebastian Goldt, Alessandro Laio

Journal ref Advances in Neural Information Processing Systems 35 (2022)

Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics

Harsh Rangwani, Shrinivas Ramasubramanian, Sho Takemori, Kato Takashi, Yuhei Umeda, Venkatesh Babu Radhakrishnan

Comments NeurIPS 2022. Code: https://github.com/val-iisc/CostSensitiveSelfTraining

Visual Referential Games Further the Emergence of Disentangled Representations

Kevin Denamganaï, Sondess Missaoui, James Alfred Walker

Comments Rejected from NeurIPS 2021 (scores of 6,6,4, and 4) / still work in progress

Matrix Multiplicative Weights Updates in Quantum Zero-Sum Games: Conservation Laws & Recurrence

Rahul Jain, Georgios Piliouras, Ryann Sim

Comments NeurIPS 2022

Semantic Exploration from Language Abstractions and Pretrained Representations

Allison C. Tam, Neil C. Rabinowitz, Andrew K. Lampinen, Nicholas A. Roy, Stephanie C. Y. Chan, DJ Strouse, Jane X. Wang, Andrea Banino, Felix Hill

Comments NeurIPS 2022

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna, Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Zohreh Shams, Frederic Precioso, Stefano Melacci, Adrian Weller, Pietro Lio, Mateja Jamnik

Comments To appear at NeurIPS 2022

Journal ref https://proceedings.neurips.cc/paper_files/paper/2022/hash/867c06823281e506e8059f5c13a57f75-Abstract-Conference.html

Free Probability for predicting the performance of feed-forward fully connected neural networks

Reda Chhaibi, Tariq Daouda, Ezechiel Kahn

Comments 20 pages, many figures ; v1: Preliminary version ; v2: Added numerical benchmarks, and changed presentation; v3: Accepted in Neurips2022

Journal ref Advances in Neural Information Processing Systems (NeurIPS), Vol 35, 2439--2450, 2022

SALSA: Attacking Lattice Cryptography with Transformers

Emily Wenger, Mingjie Chen, François Charton, Kristin Lauter

Comments Extended version of work published at NeurIPS 2022

Beyond neural scaling laws: beating power law scaling via data pruning

Ben Sorscher, Robert Geirhos, Shashank Shekhar, Surya Ganguli, Ari S. Morcos

Comments Outstanding Paper Award @ NeurIPS 2022. Added github link to metric scores

GREED: A Neural Framework for Learning Graph Distance Functions

Rishabh Ranjan, Siddharth Grover, Sourav Medya, Venkatesan Chakaravarthy, Yogish Sabharwal, Sayan Ranu

Comments Published as a conference paper at NeurIPS 2022

Advancing Model Pruning via Bi-level Optimization

Yihua Zhang, Yuguang Yao, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, Sijia Liu

Comments Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)

The Design Space of Generative Models

Meredith Ringel Morris, Carrie J. Cai, Jess Holbrook, Chinmay Kulkarni, Michael Terry

Journal ref NeurIps 2022 Human-Centered AI Workshop

Curriculum learning for multilevel budgeted combinatorial problems

Adel Nabli, Margarida Carvalho

Comments NeurIPS 2020, December 2020

State-specific protein-ligand complex structure prediction with a multi-scale deep generative model

Zhuoran Qiao, Weili Nie, Arash Vahdat, Thomas F. Miller, Anima Anandkumar

Comments 19 pages, 5 figures, 1 table & Supplementary Information (18 pages, 2 figures, 7 tables, 12 algorithms); supersedes an earlier version arXiv:2209.15171v1 presented at the NeurIPS 2022 MLSB workshop as a contributed talk

Comparing radiologists' gaze and saliency maps generated by interpretability methods for chest x-rays

Ricardo Bigolin Lanfredi, Ambuj Arora, Trafton Drew, Joyce D. Schroeder, Tolga Tasdizen

Comments This paper was presented as an Extended Abstract at the Gaze Meets ML 2022 Workshop, a NeurIPS 2022 workshop