Timezone: »

Learning to Adapt to Evolving Domains
Hong Liu · Mingsheng Long · Jianmin Wang · Yu Wang

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #683

Domain adaptation aims at knowledge transfer from a labeled source domain to an unlabeled target domain. Current domain adaptation methods have made substantial advances in adapting discrete domains. However, this can be unrealistic in real-world applications, where target data usually comes in an online and continually evolving manner as small batches, posing challenges to classic domain adaptation paradigm: (1) Mainstream domain adaptation methods are tailored to stationary target domains, and can fail in non-stationary environments. (2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i.e. to adapt without forgetting. To tackle these challenges, we propose a meta-adaptation framework which enables the learner to adapt to continually evolving target domain without catastrophic forgetting. Our framework comprises of two components: a meta-objective of learning representations to adapt to evolving domains, enabling meta-learning for unsupervised domain adaptation; and a meta-adapter for learning to adapt without forgetting, reserving knowledge from previous target data. Experiments validate the effectiveness our method on evolving target domains.

Author Information

Hong Liu (Tsinghua University)
Mingsheng Long (Tsinghua University)
Jianmin Wang (Tsinghua University)
Yu Wang (Tsinghua Univ.)

More from the Same Authors