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

PolyViT: Co-training Vision Transformers on Images, Videos and Audio


Nov 25, 2021
Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller, Mostafa Dehghani


  Access Paper or Ask Questions

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence


Nov 18, 2021
Xiang Bai, Hanchen Wang, Liya Ma, Yongchao Xu, Jiefeng Gan, Ziwei Fan, Fan Yang, Ke Ma, Jiehua Yang, Song Bai, Chang Shu, Xinyu Zou, Renhao Huang, Changzheng Zhang, Xiaowu Liu, Dandan Tu, Chuou Xu, Wenqing Zhang, Xi Wang, Anguo Chen, Yu Zeng, Dehua Yang, Ming-Wei Wang, Nagaraj Holalkere, Neil J. Halin, Ihab R. Kamel, Jia Wu, Xuehua Peng, Xiang Wang, Jianbo Shao, Pattanasak Mongkolwat, Jianjun Zhang, Weiyang Liu, Michael Roberts, Zhongzhao Teng, Lucian Beer, Lorena Escudero Sanchez, Evis Sala, Daniel Rubin, Adrian Weller, Joan Lasenby, Chuangsheng Zheng, Jianming Wang, Zhen Li, Carola-Bibiane Schönlieb, Tian Xia

* Nature Machine Intelligence 

  Access Paper or Ask Questions

Iterative Teaching by Label Synthesis


Nov 10, 2021
Weiyang Liu, Zhen Liu, Hanchen Wang, Liam Paull, Bernhard Schölkopf, Adrian Weller

* NeurIPS 2021 Spotlight (v2: 28 pages, 20 figures) 

  Access Paper or Ask Questions

Hybrid Random Features


Oct 13, 2021
Krzysztof Choromanski, Haoxian Chen, Han Lin, Yuanzhe Ma, Arijit Sehanobish, Deepali Jain, Michael S Ryoo, Jake Varley, Andy Zeng, Valerii Likhosherstov, Dmitry Kalashnikov, Vikas Sindhwani, Adrian Weller


  Access Paper or Ask Questions

SphereFace Revived: Unifying Hyperspherical Face Recognition


Sep 12, 2021
Weiyang Liu, Yandong Wen, Bhiksha Raj, Rita Singh, Adrian Weller

* Technical Report (15 pages) 

  Access Paper or Ask Questions

SphereFace2: Binary Classification is All You Need for Deep Face Recognition


Aug 03, 2021
Yandong Wen, Weiyang Liu, Adrian Weller, Bhiksha Raj, Rita Singh

* Technical Report (11 pages) 

  Access Paper or Ask Questions

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

δ-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 Liò, 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

$δ$-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 Schölkopf, 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 Antorán, Q. Vera Liao, Prasanna Sattigeri, Riccardo Fogliato, Gabrielle Gauthier Melançon, 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 Liò, 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 Kügelgen, Umang Bhatt, Amir-Hossein Karimi, Isabel Valera, Adrian Weller, Bernhard Schölkopf


  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