Timezone: »

 
Poster
Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
Zhiyu Yao · Yunbo Wang · Mingsheng Long · Jianmin Wang

Wed Jul 15 04:00 PM -- 04:45 PM & Thu Jul 16 04:00 AM -- 04:45 AM (PDT) @
in Poster Session 30 »

This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that focus on fixing the discrepancy between supervised tasks, we study how to transfer knowledge from a zoo of unsupervisedly learned models towards another predictive network. Our motivation is that models from different sources are expected to understand the complex spatiotemporal dynamics from different perspectives, thereby effectively supplementing the new task, even if the task has sufficient training samples. Technically, we propose a differentiable framework named transferable memory. It adaptively distills knowledge from a bank of memory states of multiple pretrained RNNs, and applies it to the target network via a novel recurrent structure called the Transferable Memory Unit (TMU). Compared with finetuning, our approach yields significant improvements on three benchmarks for spatiotemporal prediction, and benefits the target task even from less relevant pretext ones.

Keywords: Deep Sequence Models · Transfer and Multitask Learning · Sequential, Network, and Time-Series Modeling

Author Information

Zhiyu Yao (Tsinghua University)
Yunbo Wang (Tsinghua University)
Mingsheng Long (Tsinghua University)
Jianmin Wang (Tsinghua University)

More from the Same Authors