Timezone: »

 
Poster
Domain Aggregation Networks for Multi-Source Domain Adaptation
Junfeng Wen · Russell Greiner · Dale Schuurmans

Thu Jul 16 08:00 AM -- 08:45 AM & Thu Jul 16 07:00 PM -- 07:45 PM (PDT) @ None #None

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.

Author Information

Junfeng Wen (University of Alberta)
Russell Greiner (U Alberta)
Dale Schuurmans (University of Alberta)

More from the Same Authors