Workshop

WeaSuL 2021


Workshop on Weakly Supervised Learning

ICLR 2021 Workshop
May 7 2021
virtual


Accepted Papers

The Proceedings can be found here or on arXiv.org.

  • TADPOLE: Task ADapted Pre-training via anOmaLy dEtection
    Vivek Madan, Ashish Khetan and Zohar Karnin | Paper
  • CIGMO: Learning categorical invariant deep generative models from grouped data
    Haruo Hosoya | Paper
  • Handling Long-Tail Queries with Slice-Aware Conversational Systems
    Cheng Wang, Sun Kim, Taiwoo Park,Sajal Choudhary, Sunghyun Park, Young-Bum Kim, Ruhi Sarikaya and Sungjin Lee | Paper
  • Tabular Data Modeling via Contextual Embeddings
    Xin Huang, Ashish Khetan, Milan Cvitkovic and Zohar Karnin | Paper
  • Pre-Training by Completing Points Cloud
    Hanchen Wang, Liu Qi, Xiangyu Yue, Matt Kusner and Joan Lasenby | (non-archival)
  • AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction
    Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan and Xiang Ren | (non-archival)
  • Active WeaSuL: Improving Weak Supervision with Active Learning
    Samantha R Biegel, Rafah El-Khatib, Luiz Otavio Vilas Boas Oliveira, Max Baak and Nanne Aben | Paper | Code
  • Dependency Structure Misspecification in Multi-Source Weak Supervision Models
    Salva Rühling Cachay, Benedikt Boecking and Artur Dubrawski | Paper
  • Weakly-Supervised Group Disentanglement using Total Correlation
    Linh Tran, Saeid Asgari Taghanaki, Amir Hosein Khasahmadi, Aditya Sanghi | Paper
  • Better adaptation to distribution shifts with Robust Pseudo-Labeling
    Evgenia Rusak, Steffen Schneider, Peter Gehler, Oliver Bringmann, Bernhard Schölkopf, Wieland Brendel and Matthias Bethge | (non-archival)
  • Transformer Language Models as Universal Computation Engines
    Kevin Lu, Aditya Grover, Pieter Abbeel and Igor Mordatch | (non-archival)
  • Using system context information to complement weakly labeled data
    Matthias Meyer, Michaela Wenner, Clément Hibert, Fabian Walter and Lothar Thiele | Paper | Code
  • Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches
    Dmitry Kazhdan, Botty Dimanov, Helena Andres Terre, Pietro Lió, Mateja Jamnik and Adrian Weller | (non-archival) | Code
  • Weakly Supervised Multi-task Learning for Concept-based Explainability
    Vladimir Balayan, Catarina G Belém, Pedro Saleiro and Pedro Bizarro | Paper
  • Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks
    Curtis G Northcutt, Anish Athalye and Jonas Mueller | Paper | Code