Domain Aggregation Networks for Multi-Source Domain Adaptation
12. července 2020
Řečníci
Junfeng Wen
Řečník · 0 sledujících
Dale Schuurmans
Řečník · 2 sledující
Russ Greiner
Řečník · 0 sledujících
O prezentaci
In many real-world applications, we want to exploit multiple source datasets to build a model for a different but related target dataset. Despite the recent empirical success, most existing research has used ad-hoc methods to combine multiple sources, leading to a gap between theory and practice. In this paper, we develop a finite-sample generalization bound based on domain discrepancy and accordingly propose a theoretically justified optimization procedure. Our algorithm, Domain AggRegation Network (DARN), can automatically and dynamically balance between including more data to increase effective sample size and excluding irrelevant data to avoid negative effects during training. We find that DARN can significantly outperform the state-of-the-art alternatives on multiple real-world tasks, including digit/object recognition and sentiment analysis.In many real-world applications, we want to exploit multiple source datasets to build a model for a different but related target dataset. Despite the recent empirical success, most existing research has used ad-hoc methods to combine multiple sources, leading to a gap between theory and practice. In this paper, we develop a finite-sample generalization bound based on domain discrepancy and accordingly propose a theoretically justified optimization procedure. Our algorithm, Domain AggRegation Net…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
“Other-Play” for Zero-Shot Coordination
Zhlédnout později
Hengyuan Hu, …
An EM Approach to Non-autoregressive Conditional Sequence Generation
Zhlédnout později
Zhiqing Sun, …
Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
Zhlédnout později
Zhe Zeng, …
Towards multi-agent emergent communication as a building block of human-centric AI
Zhlédnout později
Batch Reinforcement Learning with Hyperparameter Gradients
Zhlédnout později
