Accepted Papers

We received a number of high-quality submissions to SubSetML 2021. We have accepted 32 papers as spotlight presentations and 13 papers as posters, making the total number of accepted papers 45. The full list of accepted papers is here.

Spotlight Papers

  1. Supratim Shit (Technion)*; Rachit Chhaya (IIT Gandhinagar); Anirban Dasgupta (IIT Gandhinagar); Jayesh Choudhari (IIT Gandhinagar), Online and Non Parametric Coresets for Bregman Divergence

  2. Tianyuan Jin (National University of Singapore)*; Yu Yang (City University of Hong Kong); Renchi Yang (National University of Singapore); Jieming Shi (The Hong Kong Polytechnic University); Keke Huang (Nanyang Technological University); Xiaokui Xiao (National University of Singapore), Unconstrained Submodular Maximization with Modular Costs: Tight Approximation and Application to Profit Maximization

  3. Noveen Sachdeva (UC San Diego)*; Carole-Jean Wu (Facebook AI Research); Julian McAuley (UCSD), SVP-CF: Selection via Proxy for Collaborative Filtering Data

  4. Daniel R Kowal (Rice University)*, Bayesian decision analysis for collecting nearly-optimal subsets

  5. Rina Onda (The University of Tokyo ); Gao Zhengyan (Preferred Networks); Masaaki Kotera (Preferred Networks); Kenta Oono (Preferred Networks)*, Fast Estimation Method for the Stability of Ensemble Feature Selectors

  6. Kyeongbo Kong (POSTECH); Kyunghun Kim (Sogang University); Woo-jin Song (POSTECH); Suk-Ju Kang (Sogang University)*, Selective Focusing Learning in Conditional GANs

  7. Raaz Dwivedi (UNIVERSITY OF CALIFORNIA Berkeley)*; Lester Mackey (Microsoft Research New England), Kernel Thinning

  8. Xueying ZHAN (City University of Hong Kong)*; Qing Li (The Hong Kong Polytechnic University ); Antoni Chan (City University of Hong Kong, Hong, Kong), Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes

  9. Anup Rao (Adobe Research)*; Tung Mai (Adobe Research); Cameron Musco (University of Massachusetts Amherst), Coresets for Classification – Simplified and Strengthened

  10. Ubai Sandouk (Damascus University)*, Using Machine Learning to Recognise Statistical Dependence

  11. Kyeongbo Kong (POSTECH)*; Junggi Lee (POSTECH); Youngchul Kwak (POSTECH); Young-Rae Cho (Samsung electronics ); Seong-Eun Kim (Seoul National University of Science and Technology); Woo-jin Song (POSTECH), Mitigating Memorization in Sample Selection for Learning with Noisy Labels

  12. Michał Pietruszka (Jagiellonian University)*; Łukasz Borchmann (Applica.ai); Łukasz Garncarek (Applica.ai), Sparsifying Transformer Models with Trainable Representation Pooling

  13. Tim G. J. Rudner (University of Oxford)*; Freddie Bickford Smith (University of Oxford); Qixuan FENG (University of Oxford); Yee Whye Teh (University of Oxford); Yarin Gal (University of Oxford), Continual Learning via Function-Space Variational Inference: A Unifying View

  14. Andreas Kirsch (University of Oxford)*; Tom Rainforth (University of Oxford); Yarin Gal (University of Oxford), Active Learning under Pool Set Distribution Shift and Noisy Data

  15. Sebastian E Ament (Cornell University)*; Carla P Gomes (Cornell University), Sparse Bayesian Learning via Stepwise Regression

  16. Raj Agrawal (MIT)*; Tamara Broderick (MIT), High-Dimensional Variable Selection and Non-Linear Interaction Discovery in Linear Time

  17. Abhijeet Awasthi (Indian Institute of Technology Bombay)*; Aman Kansal (IIT Bombay); Sunita Sarawagi (Indian Institute of Technology); Preethi Jyothi (Indian Institute of Technology Bombay), Error-driven Fixed-Budget ASR Personalization for Accented Speakers

  18. Zhiqi Bu (University of Pennsylvania); Zongyu Dai (University of Pennsylvania)*; Yiliang Zhang (University of Pennsylvania); Qi Long (University of Pennsylvania), MISNN: Multiple Imputation via Semi-parametric Neural Networks

  19. Zeel B Patel (IIT Gandhinagar)*; Nipun Batra (IIT Gandhinagar), Towards Active Air Quality Station Deployment

  20. Jae-hun Shim (Sogang University); Kyeongbo Kong (POSTECH); Suk-Ju Kang (Sogang University)*, Core-set Sampling for Efficient Neural Architecture Search

  21. Rachit Chhaya (IIT Gandhinagar)*; Anirban Dasgupta (IIT Gandhinagar); Supratim Shit (Technion); Jayesh Choudhari (IIT Gandhinagar), On Coresets For Fair Regression

  22. Timo Bertram (Johannes-Kepler Universität)*; Johannes Fürnkranz (JKU Linz); Martin Müller (University of Alberta), A Comparison of Contextual and Non-Contextual Preference Ranking for Set Addition Problems

  23. Vinu Sankar Sadasivan (Indian Institute of Technology Gandhinagar)*; Anirban Dasgupta (IIT Gandhinagar), Statistical Measures For Defining Curriculum Scoring Function

  24. Srikanth Banagere Manjunatha (Pennsylvania State University); Viveck Cadambe (Penn State)*; Bill Kay (Oak Ridge National Laboratory), An Extreme Point Approach to Subset Selection

  25. Gantavya Bhatt (University of Washington, Seattle)*; Jeff Bilmes (UW), Tighter m-DPP Coreset Sample Complexity Bounds

  26. Suraj Kothawade (UT Dallas)*; Nathan Beck (UT Dallas); Krishnateja Killamsetty (University of Texas at Dallas); Rishabh Iyer (University of Texas at Dallas), SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios

  27. Arman Adibi (University of Pennsylvania)*; Aryan Mokhtari (UT Austin); Hamed Hassani (University of Pennsylvania), Minimax Optimization: The Case of Convex-Submodular

  28. Omid Sadeghi (University of Washington)*; Maryam Fazel (University of Washington), Improved Regret Bounds for Online Submodular Maximization

  29. Omid Sadeghi (University of Washington)*; Maryam Fazel (University of Washington), Differentially Private Monotone Submodular Maximization Under Matroid and Knapsack Constraints

  30. Nathan A Beck (The University of Texas at Dallas)*; Durga S (Indian Institute of Technology Bombay); Apurva Dani (AIFY Innovation Labs); Ganesh Ramakrishnan (IIT Bombay); Rishabh Iyer (University of Texas at Dallas), Effective Evaluation of Deep Active Learning on Image Classification Tasks

  31. Maximilian Thiessen (TU Wien)*; Thomas Gärtner (TU Wien), Active Learning Convex Halfspaces on Graphs

  32. Praneeth Vepakomma (MIT)*; Yulia Kempner (HIT); Ramesh Raskar (MIT), Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity


Posters

  1. Francesco Farina (GlaxoSmithKline); Emma Slade (GlaxoSmithKline)*, Data efficiency in graph networks through equivariance

  2. Celia Cintas (IBM Research Africa)*; Skyler D Speakman (IBM Research); Girmaw Abebe Tadesse (IBM); Victor Akinwande (IBM Research); Edward McFowland III (Harvard Business School, Harvard University); Komminist Weldemariam (IBM Research), SubsetGAN: Pattern detection in the activation space for Identifying Synthesised Content

  3. Aissatou Diallo (Technische Universität Darmstadt)*; Johannes Fürnkranz (JKU Linz), Ordinal Embedding for Sets

  4. Nicolo Colombo (Royal Holloway University of London)*; Yang Gao (Royal Holloway University of London), Differentiable architecture pruning for transfer learning

  5. Niel Hu (ML Collective)*; Xinyu Hu (Uber); Rosanne Liu (ML Collective); Sara Hooker (Google Brain); Jason Yosinski (ML Collective), When does loss-based prioritization fail?

  6. Shril Mody (IIT Gandhinagar)*; Janvi Thakkar (IIT Gandhinagar); Devvrat Joshi (IIT Gandhinagar); Siddharth Soni (IIT Gandhinagar); Nipun Batra (IIT Gandhinagar); Rohan P Patil (Indian Institue of Technology Gandhinagar), Geometrical Homogeneous Clustering for Image Data Reduction

  7. Farhad Pourkamali-Anaraki (University of Massachusetts Lowell)*; Walter Bennette (AFRL), Interactive Teaching for Imbalanced Data Summarization

  8. Andreas Kirsch (University of Oxford)*; Yarin Gal (University of Oxford), A Practical Notation for Information-Theoretic Quantities between Outcomes and Random Variables

  9. Sirui Li (MIT)*; Zhongxia Yan (MIT); Cathy Wu (), Learning to Delegate for Large-scale Vehicle Routing

  10. Rishabh Mehrotra (Spotify)*, Multi-objective diversification via Submodular Counterfactual Scoring for Track Sequencing on Spotify

  11. Savan Amitbhai Visalpara (The University of Texas at Dallas)*; Krishnateja Killamsetty (The University of Texas at Dallas); Rishabh Iyer (The University of Texas at Dallas), A Data Subset Selection Framework for Efficient Hyper-Parameter Tuning and Automatic Machine Learning

  12. Sören Mindermann (Vector Institute)*; Muhammed T Razzak (University of Oxford); Winnie Xu (University of Toronto); Andreas Kirsch (University of Oxford); Mrinank Sharma (University of Oxford); Adrien Morisot (Independent Researcher); Aidan N Gomez (Google); Sebastian Farquhar (University of Oxford); Jan M Brauner (University of Oxford); Yarin Gal (University of Oxford), Prioritized training on points that are learnable, worth learning, and not yet learned

  13. Andreas Kirsch (University of Oxford)*; Sebastian Farquhar (University of Oxford); Yarin Gal (University of Oxford), Batch Active Learning with Stochastic Acquisition Functions

  14. Alaa Maalouf, Gilad Eini, Ben Mussay, Dan Feldman, Margarita Osadchy, AutoCL: Automatic Coreset Learning