迁移学习
- 定义：用其他领域已经训练好的模型，迁移到本领域使用（类似于举一反三）
- 优点： 1、 小数据量即可 2、 模型已经训练好了 3、节省成本，不需要重新学习
- 迁移学习的优势： 1、 personalization 2、 一个模型可以多领域使用
- 关键点：找到不变量
Recent Works in Transfer Learning
• Ben Tan, Yangqiu Song, Erheng Zhong, Qiang Yang: Transitive Transfer Learning. KDD 2015 • Ben Tan, Yangqiu Song, Erheng Zhong, Qiang Yang: Transitive Transfer Learning. KDD 2015Ben Tan, Yu Zhang, Sinno Jialin Pan, Qiang Yang: Distant Domain Transfer Learning. AAAI 2017 • Zheng Li, Yu Zhang, Ying Wei, Yuxiang Wu, Qiang Yang, End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification, IJCAI 2017 • Zheng Li, Ying Wei, Yu Zhang, Qiang Yang, Hierarchical Attention Transfer Network for Cross-domain Sentiment Classification, AAAI 2018 • Kaixiang Mo, Yu Zhang, Shuangyin Li, Jiajun Li, Qiang Yang, Personalizing a Dialogue System with Transfer Reinforcement Learning, AAAI 2018. • Bo Liu, Ying Wei, Yu Zhang, Zhixian Yan, Qiang Yang, Transferable Contextual Bandit for Cross-Domain Recommendation, AAAI 2018 — e.g. 不同领域（政治、经济、电影）的评论模型可以直接迁移
- challenge：不同领域的评价词的等效性与区别；