Accepted Papers

  1. TuckER: Tensor Factorization for Knowledge Graph Completion
  2. Learning Cancer Outcomes from Heterogeneous Genomic Data Sources: An Adversarial Multi-task Learning Approach
  3. Continual adaptation for efficient machine communication (Oral Presentation)
  4. Every Sample a Task: Pushing the Limits of Heterogeneous Models with Personalized Regression
  5. Data Enrichment: Multi-task Learning in High Dimension with Theoretical Guarantees
  6. A Functional Extension of Multi-Output Learning
  7. Interpretable Robust Recommender Systems with Side Information
  8. Personalized Student Stress Prediction with Deep Multi-Task Network
  9. SuperTML: Domain Transfer from Computer Vision to Structured Tabular Data through Two-Dimensional Word Embedding
  10. Goal-conditioned Imitation Learning
  11. Tasks Without Borders: A New Approach to Online Multi-Task Learning
  12. The Role of Embedding-complexity in Domain-invariant Representations
  13. Lifelong Learning via Online Leverage Score Sampling (Oral Presentation)
  14. Connections Between Optimization in Machine Learning and Adaptive Control
  15. Meta-Reinforcement Learning for Adaptive Autonomous Driving
  16. PAGANDA: An Adaptive Task-Independent Automatic Data Augmentation
  17. Improving Relevance Prediction with Transfer Learning in Large-scale Retrieval Systems (Oral Presentation)
  18. Federated Optimization for Heterogeneous Networks
  19. Learning Exploration Policies for Model-Agnostic Meta-Reinforcement Learning (Oral Presentation)
  20. A Meta Understanding of Meta-Learning
  21. Multi-Task Learning via Task Multi-Clustering
  22. Prototypical Bregman Networks
  23. Differentiable Hebbian Plasticity for Continual Learning
  24. Active Multitask Learning with Committees
  25. Progressive Memory Banks for Incremental Domain Adaptation
  26. Sub-policy Adaptation for Hierarchical Reinforcement Learning
  27. Learning to learn to communicate