- TuckER: Tensor Factorization for Knowledge Graph Completion
- Learning Cancer Outcomes from Heterogeneous Genomic Data Sources: An Adversarial Multi-task Learning Approach
- Continual adaptation for efficient machine communication (Oral Presentation)
- Every Sample a Task: Pushing the Limits of Heterogeneous Models with Personalized Regression
- Data Enrichment: Multi-task Learning in High Dimension with Theoretical Guarantees
- A Functional Extension of Multi-Output Learning
- Interpretable Robust Recommender Systems with Side Information
- Personalized Student Stress Prediction with Deep Multi-Task Network
- SuperTML: Domain Transfer from Computer Vision to Structured Tabular Data through Two-Dimensional Word Embedding
- Goal-conditioned Imitation Learning
- Tasks Without Borders: A New Approach to Online Multi-Task Learning
- The Role of Embedding-complexity in Domain-invariant Representations
- Lifelong Learning via Online Leverage Score Sampling (Oral Presentation)
- Connections Between Optimization in Machine Learning and Adaptive Control
- Meta-Reinforcement Learning for Adaptive Autonomous Driving
- PAGANDA: An Adaptive Task-Independent Automatic Data Augmentation
- Improving Relevance Prediction with Transfer Learning in Large-scale Retrieval Systems (Oral Presentation)
- Authors: Ruoxi Wang, Zhe Zhao, Xinyang Yi, Ji Yang, Derek Zhiyuan Cheng, Lichan Hong, Steve Tjoa, Jieqi Kang, Evan Ettinger, Ed Chi
- Links: OpenReview, PDF
- Federated Optimization for Heterogeneous Networks
- Learning Exploration Policies for Model-Agnostic Meta-Reinforcement Learning (Oral Presentation)
- A Meta Understanding of Meta-Learning
- Multi-Task Learning via Task Multi-Clustering
- Prototypical Bregman Networks
- Differentiable Hebbian Plasticity for Continual Learning
- Active Multitask Learning with Committees
- Progressive Memory Banks for Incremental Domain Adaptation
- Sub-policy Adaptation for Hierarchical Reinforcement Learning
- Learning to learn to communicate