Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Adrian Weller

DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement


Jul 13, 2021
Umang Bhatt, Isabel Chien, Muhammad Bilal Zafar, Adrian Weller

* 30 pages, 32 figures 

  Access Paper or Ask Questions

Debiasing a First-order Heuristic for Approximate Bi-level Optimization


Jun 08, 2021
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski, Jared Davis, Adrian Weller

* Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021. arXiv admin note: text overlap with arXiv:2006.03631 

  Access Paper or Ask Questions

On the Expressive Power of Self-Attention Matrices


Jun 08, 2021
Valerii Likhosherstov, Krzysztof Choromanski, Adrian Weller


  Access Paper or Ask Questions

Do Concept Bottleneck Models Learn as Intended?


May 10, 2021
Andrei Margeloiu, Matthew Ashman, Umang Bhatt, Yanzhi Chen, Mateja Jamnik, Adrian Weller

* Accepted at ICLR 2021 Workshop on Responsible AI 

  Access Paper or Ask Questions

╬┤-CLUE: Diverse Sets of Explanations for Uncertainty Estimates


May 08, 2021
Dan Ley, Umang Bhatt, Adrian Weller

* Appeared as a workshop paper at ICLR 2021 (Responsible AI | Secure ML | Robust ML) 

  Access Paper or Ask Questions

CrossWalk: Fairness-enhanced Node Representation Learning


May 06, 2021
Ahmad Khajehnejad, Moein Khajehnejad, Mahmoudreza Babaei, Krishna P. Gummadi, Adrian Weller, Baharan Mirzasoleiman


  Access Paper or Ask Questions

Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches


Apr 14, 2021
Dmitry Kazhdan, Botty Dimanov, Helena Andres Terre, Mateja Jamnik, Pietro Li├▓, Adrian Weller

* Presented at the RAI, WeaSul, and RobustML workshops at The Ninth International Conference on Learning Representations (ICLR) 2021 

  Access Paper or Ask Questions

$╬┤$-CLUE: Diverse Sets of Explanations for Uncertainty Estimates


Apr 14, 2021
Dan Ley, Umang Bhatt, Adrian Weller

* Appeared as a workshop paper at ICLR 2021 (Responsible AI | Secure ML | Robust ML) 

  Access Paper or Ask Questions

Unlocking Pixels for Reinforcement Learning via Implicit Attention


Mar 04, 2021
Krzysztof Choromanski, Deepali Jain, Jack Parker-Holder, Xingyou Song, Valerii Likhosherstov, Anirban Santara, Aldo Pacchiano, Yunhao Tang, Adrian Weller


  Access Paper or Ask Questions

Learning with Hyperspherical Uniformity


Mar 02, 2021
Weiyang Liu, Rongmei Lin, Zhen Liu, Li Xiong, Bernhard Sch├Âlkopf, Adrian Weller

* AISTATS 2021 

  Access Paper or Ask Questions

Sub-Linear Memory: How to Make Performers SLiM


Dec 21, 2020
Valerii Likhosherstov, Krzysztof Choromanski, Jared Davis, Xingyou Song, Adrian Weller


  Access Paper or Ask Questions

Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training


Dec 02, 2020
Andrei Margeloiu, Nikola Simidjievski, Mateja Jamnik, Adrian Weller

* To appear at NeurIPS 2020 workshop "Medical Imaging meets NeurIPS (MED-NEURIPS)" 

  Access Paper or Ask Questions

Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty


Nov 15, 2020
Umang Bhatt, Yunfeng Zhang, Javier Antor├ín, Q. Vera Liao, Prasanna Sattigeri, Riccardo Fogliato, Gabrielle Gauthier Melan├žon, Ranganath Krishnan, Jason Stanley, Omesh Tickoo, Lama Nachman, Rumi Chunara, Adrian Weller, Alice Xiang

* 19 pages, 6 figures 

  Access Paper or Ask Questions

Now You See Me (CME): Concept-based Model Extraction


Oct 25, 2020
Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik, Pietro Li├▓, Adrian Weller

* Presented at the AIMLAI workshop at the 29th ACM International Conference on Information and Knowledge Management (CIKM 2020) 

  Access Paper or Ask Questions

On the Fairness of Causal Algorithmic Recourse


Oct 14, 2020
Julius von K├╝gelgen, Umang Bhatt, Amir-Hossein Karimi, Isabel Valera, Adrian Weller, Bernhard Sch├Âlkopf


  Access Paper or Ask Questions

Rethinking Attention with Performers


Sep 30, 2020
Krzysztof Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Davis, Afroz Mohiuddin, Lukasz Kaiser, David Belanger, Lucy Colwell, Adrian Weller

* 36 pages. This is an updated version of a previous submission which can be found at arXiv:2006.03555. See https://github.com/google-research/google-research/tree/master/protein_lm for protein language model code, and https://github.com/google-research/google-research/tree/master/performer for Performer code 

  Access Paper or Ask Questions

Machine Learning Explainability for External Stakeholders


Jul 10, 2020
Umang Bhatt, McKane Andrus, Adrian Weller, Alice Xiang


  Access Paper or Ask Questions

An Ode to an ODE


Jun 23, 2020
Krzysztof Choromanski, Jared Quincy Davis, Valerii Likhosherstov, Xingyou Song, Jean-Jacques Slotine, Jacob Varley, Honglak Lee, Adrian Weller, Vikas Sindhwani

* 20 pages, 9 figures 

  Access Paper or Ask Questions

Getting a CLUE: A Method for Explaining Uncertainty Estimates


Jun 11, 2020
Javier Antor├ín, Umang Bhatt, Tameem Adel, Adrian Weller, Jos├ę Miguel Hern├índez-Lobato

* 33 pages, 31 figures 

  Access Paper or Ask Questions

UFO-BLO: Unbiased First-Order Bilevel Optimization


Jun 05, 2020
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski, Jared Davis, Adrian Weller


  Access Paper or Ask Questions

Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers


Jun 05, 2020
Krzysztof Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Jared Davis, Tamas Sarlos, David Belanger, Lucy Colwell, Adrian Weller

* 14 pages, 11 figures 

  Access Paper or Ask Questions

Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks


May 11, 2020
Moein Khajehnejad, Ahmad Asgharian Rezaei, Mahmoudreza Babaei, Jessica Hoffmann, Mahdi Jalili, Adrian Weller

* In Proc. of the 29th International Joint Conference on Artificial Intelligence (IJCAI'20), 2020 

  Access Paper or Ask Questions

Time Dependence in Non-Autonomous Neural ODEs


May 06, 2020
Jared Quincy Davis, Krzysztof Choromanski, Jake Varley, Honglak Lee, Jean-Jacques Slotine, Valerii Likhosterov, Adrian Weller, Ameesh Makadia, Vikas Sindhwani


  Access Paper or Ask Questions