Log inSign up
user avatar
Shiori Sagawa
@shiorisagawa
Researcher @OpenAI. Previously, CS PhD @StanfordAILab
Stanford, CA
cs.stanford.edu/~ssagawa
Joined July 2020
235
Following
1,791
Followers
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Dec 15, 2020
    We're excited to announce WILDS, a benchmark of in-the-wild distribution shifts with 7 datasets across diverse data modalities and real-world applications. Website: wilds.stanford.edu Paper: arxiv.org/abs/2012.07421 Github: github.com/p-lambda/wilds Thread below. (1/12)
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Mar 11, 2021
    We’ve released v1.1 of WILDS, our benchmark of in-the-wild distribution shifts! This adds the Py150 dataset for code completion + updates to existing datasets to make them faster and easier to use. Website: wilds.stanford.edu Paper: arxiv.org/abs/2012.07421 Thread 👇 (1/8)
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Apr 27, 2022
    We’ll be presenting WILDS v2.0 as an oral at ICLR! We extended the WILDS benchmark of real-world shifts by adding unlabeled data, which can be used for domain adaptation and representation learning. Talk + poster: iclr.cc/virtual/2022/o… Paper: arxiv.org/abs/2112.05090 🧵
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Aug 25, 2021
    We’ll be organizing a NeurIPS Workshop on Distribution Shifts! We’ll focus on bringing together applications and methods to facilitate discussion on real-world distribution shifts. Website: sites.google.com/view/distshift… Submission deadline: Oct 8 Workshop date: Dec 13
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Jul 19, 2021
    Just in time for ICML, we’re announcing WILDS v1.2! We've updated our paper and added two new datasets with real-world distribution shifts. Website: wilds.stanford.edu Paper: arxiv.org/abs/2012.07421 ICML: icml.cc/virtual/2021/p… Blog🆕: ai.stanford.edu/blog/wilds/ 🧵(1/9)
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Dec 2, 2022
    Join us at the NeurIPS Workshop on Distribution Shifts (DistShift) tomorrow! When: Saturday, Dec 3, 9am-5pm Where: Room 388 - 390 Website: sites.google.com/view/distshift… Virtual site: neurips.cc/virtual/2022/w…
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Jul 22, 2022
    I'm excited to speak at the Principles of Distribution Shift workshop at #ICML2022 tomorrow at 9:50am in Ballroom 3! I'll be talking about extending the WILDS benchmark with unlabeled data. Please join us! The talk will also be streamed at icml.cc/virtual/2022/w….
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Dec 14, 2023
    Join us at the NeurIPS Workshop on Distribution Shifts (DistShift) tomorrow! When: Friday, Dec 15, 9am-5pm Where: Room R06-R09 Website: sites.google.com/view/distshift… Virtual site: neurips.cc/virtual/2023/w…
    Image
    28K
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Sep 15, 2022
    We're excited to organize the DistShift workshop at NeurIPS 2022! Like last year, we'll focus on real-world shifts and bringing together methods and applications. Please consider submitting to the workshop!
    user avatar
    Yoonho Lee
    @yoonholeee
    Sep 15, 2022
    We're organizing the second Workshop on Distribution Shifts (DistShift) at #NeurIPS2022, which will bring together researchers and practitioners. Submission deadline: Oct 3 (AoE) Workshop date: Dec 3 Website: sites.google.com/view/distshift…
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Aug 18, 2021
    Excited to give a talk at the Rising Star Spotlights Seminar tomorrow at 9am PT! I'll talk about robustness to distribution shifts, focusing on DRO methods and the WILDS benchmark. Please join us, and thank you @trustworthy_ml for having me!
    user avatar
    Trustworthy ML Initiative (TrustML)
    @trustworthy_ml
    Aug 17, 2021
    1/ It’s Rising Star Spotlights Seminar ⭐️ time again! For this week’s TrustML seminar, we're delighted to host @shiorisagawa (Stanford) & @p_vihari (IITB) on Thurs Aug 19th 12pm ET 🎉🎉🥳 Register here: us02web.zoom.us/webinar/regist… See this thread for the speaker & talk details👇
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Jun 15, 2022
    Excited to give a talk at the Oxford Women in CS Seminar Series tomorrow, 6/16 at 9am PT! Please join us, and thank you @OxWoCS for having me!
    user avatar
    Oxford Women in Computer Science
    @OxWoCS
    Jun 13, 2022
    For our seminar speaker event this Thursday, Shiori Sagawa (@shiorisagawa) from Stanford will be talking about her work on distributionally robust optimization (DRO) as well as the WILDS benchmark 👏👏👏 Time: 5-6pm BST, Thursday, 16th June Sign up: forms.office.com/r/RbCk1ZeA9y
    Image
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Jul 22, 2022
    I'll be moderating a breakout session on OOD generalization at the SCIS workshop at #ICML2022 today at 5:45pm. Please stop by Room 340 if you're interested in joining!
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Jul 23, 2022
    Replying to @zacharylipton
    My talk was on this paper: arxiv.org/abs/2112.05090! We saw that success need not transfer across different shifts: domain adaptation algorithms, which work well on certain shifts like photos to sketches in DomainNet, often don’t work on the shifts in the WILDS benchmark.
    arXiv logo
    arxiv.org
    Extending the WILDS Benchmark for Unsupervised Adaptation
    Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for...
  • user avatar
    Shiori Sagawa
    @shiorisagawa
    Dec 15, 2020
    Replying to @shiorisagawa
    Most WILDS datasets consider the domain generalization setting, which tests generalization to unseen domains. In iWildCam, we train on photos from some camera traps, and test on other camera traps. Goal: classify animal species (for conservation/ecology). (3/12)
    Image