Nov 28 - Dec 9 2022 in New Orleans (USA)
This collection includes resources from the NeurIPS conference 2022. To add an accepted submission, please fill out the following this form. If you want to add multiple contributions, you can also adjust the conference site in our github page (https://github.com/trustworthy-ml-resources/trustworthy-ml-resources.github.io) under ‘/_conferences/neurips22.md’ and send a pull request.
If your contribution was accepted at the co-located ML4H symposium, please feel free to add it (add ML4H under session).
Times are in CST. Thank you!
Poster: A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets (Poster Session 4)
Miri Zilka · Bradley Butcher · Adrian Weller
Wed Nov 30, 4 p.m. (Hall J, #1023)
https://neurips.cc/virtual/2022/poster/55642
Poster: Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts (Poster Session 1)
Neeraj Wagh · Jionghao Wei · Samarth Rawal · Brent M. Berry · Yogatheesan Varatharajah
Tue 29 Nov, 11:30 a.m (Hall J, #523)
https://neurips.cc/virtual/2022/poster/52788
Poster: Improved techniques for deterministic L2 robustness (Poster Session 1)
Sahil Singla · Soheil Feizi
Tue 29 Nov, 11 a.m. (Hall J #641)
https://nips.cc/virtual/2022/poster/53341
Poster: What You See is What You Get: Principled Deep Learning via Distributional Generalization (Poster Session 2)
Bogdan Kulynych · Yao-Yuan Yang · Yaodong Yu · Jarosław Błasiok · Preetum Nakkiran
Tue 29 Nov 4 p.m. (Hall J #332)
https://neurips.cc/virtual/2022/poster/53983
Poster: Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity (Poster Session 2)
Andrew Cullen · Paul Montague · Shijie Liu · Sarah Erfani · Benjamin Rubinstein
Tue 29 Nov, 4 p.m. (Hall J #731)
https://nips.cc/virtual/2022/poster/53661
Poster: Toward Efficient Robust Training against Union of Lp Threat Models (Poster Session 2)
Gaurang Sriramanan · Maharshi Gor · Soheil Feizi
Tue 29 Nov 4 p.m. (Hall J #803)
https://nips.cc/virtual/2022/poster/52908
Poster: Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation (Poster Session 3)
Zhouxing Shi · Yihan Wang · Huan Zhang · J. Zico Kolter · Cho-Jui Hsieh
Wed 30 Nov, 11 a.m (Hall J, #523)
https://arxiv.org/pdf/2210.07394.pdf
Poster: Lethal Dose Conjecture on Data Poisoning (Poster Session 5)
Wenxiao Wang · Alexander Levine · Soheil Feizi
Thu 1 Dec 11 a.m. (Hall J #712)
https://arxiv.org/abs/2208.03309
Poster: Explicit Tradeoffs between Adversarial and Natural Distributional Robustness (Poster Session 5)
Mazda Moayeri · Kiarash Banihashem · Soheil Feizi
Thu 1 Dec 11 a.m. (Hall J #732)
https://arxiv.org/abs/2209.07592
Poster: Formulating Robustness Against Unforeseen Attacks (Poster Session 6)
Sihui Dai · Saeed Mahloujifar · Prateek Mittal
Thu 1 Dec, 4 p.m. (Hall J, #511)
https://arxiv.org/abs/2204.13779
Tutorial: Foundational Robustness of Foundation Models (Virtual)
Pin-Yu Chen · Sijia Liu · Sayak Paul
Mon 5 Dec, 7 a.m.
https://neurips.cc/virtual/2022/tutorial/55796
Poster: Your Out-of-Distribution Detection Method is Not Robust! (Virtual)
Mohammad Azizmalayeri · Arshia Soltani Moakhar · Arman Zarei · Reihaneh Zohrabi · Mohammad Manzuri · Mohammad Hossein Rohban
https://neurips.cc/virtual/2022/poster/53795
(Spotlight presentation: https://neurips.cc/virtual/2022/spotlight/65149, Thu 8 Dec 11:30 a.m. online)
Invited talk: A Brief History of Explainable AI: From Simple Rules to Large Pretrained Models (Affinity Workshop ‘Women in ML’)
Hima Lakkaraju (Harvard)
Mon 28 Nov, 2:35 pm (Hall I-2)
Poster: What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods (Poster Session 1)
Julien Colin · Thomas FEL · Remi Cadene · Thomas Serre
Tue 29 Nov, 11 a.m. (Hall J, #927)
https://neurips.cc/virtual/2022/poster/55282
Poster: Locating and Editing Factual Associations in GPT (Poster Session 4)
Kevin Meng · David Bau · Alex Andonian · Yonatan Belinko
Wed 30 Nov, 4 p.m. (Hall J #226)
https://neurips.cc/virtual/2022/poster/53864
Poster: Use-Case-Grounded Simulations for Explanation Evaluation (Poster Session 6)
Valerie Chen · Nari Johnson · Nicholay Topin · Gregory Plumb · Ameet Talwalkar
Thu 1 Dec, 4 p.m. (Hall J, #511)
https://arxiv.org/abs/2206.02256
Poster: Washing The Unwashable : On The (Im)possibility of Fairwashing Detection (Poster Session 6)
Ali Shahin Shamsabadi · Mohammad Yaghini · Natalie Dullerud · Sierra Wyllie · Ulrich Aïvodji · Aisha Alaagib · Sébastien Gambs · Nicolas Papernot
Thu 1 Dec, 4 p.m. (Hall J #732)
https://nips.cc/virtual/2022/poster/54741
Spotlight talk: Does the explanation satisfy your needs?: A unified view of properties of explanations (Workshop:
Progress and Challenges in Building Trustworthy Embodied AI)
Varshini Subhash · Zixi Chen · Marton Havasi · Weiwei Pan · Finale Doshi-Velez
Fri 2 Dec, 2:53 p.m (Room 281-282)
https://arxiv.org/abs/2211.05667
Poster: Bounded logit attention: Learning to explain image classifiers (Workshop: All Things Attention: Bridging Different Perspectives on Attention)
Thomas Baumhauer · Djordje Slijepcevic · Matthias Zeppelzauer
Fri 2 Dec, 1 p.m (Room 399)
https://attention-learning-workshop.github.io/2022/papers/baumhauer-bounded_logit_attention_learning_to_explain_image_classifiers.pdf
Poster: Exploiting Selection Bias on Underspecified Tasks in Large Language Models (Workshop: Causal Machine Learning for Real-World Impact Workshop)
Emily McMilin
Thu 1 Dec, 10 a.m. (Room 295-296)
https://nips.cc/virtual/2022/workshop/49993#wse-detail-61720
Social: ML Safety
David Krueger · Orpheus Lummis
Wed 30 Nov 1-3 a.m. (Room 394)
https://nips.cc/virtual/2022/social/56270
Workshop: Progress and Challenges in Building Trustworthy Embodied AI
Fri 2 Dec, 7:50 a.m. (Room 281-282)
https://sites.google.com/berkeley.edu/trustworthy-embodied-ai
Invied talk: Ethics of AI and Large Scale ML — Beyond Rules and Regulations (Workshop ‘New In ML’) Jean-Gabriel Ganascia (Sorbonne University) Mon 28 Nov 10:30 a.m. (Room 295)
Social: Ethics Review - Open Discussion
Deborah Raji · William Isaac · Cherie Poland · Alexandra Luccioni
Wed 30 Nov 1-3 a.m. (Room 395)
https://nips.cc/virtual/2022/social/56377