Timezone: »

Iterative Teacher-Aware Learning
Luyao Yuan · Dongruo Zhou · Junhong Shen · Jingdong Gao · Jeffrey L Chen · Quanquan Gu · Ying Nian Wu · Song-Chun Zhu

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @

In human pedagogy, teachers and students can interact adaptively to maximize communication efficiency. The teacher adjusts her teaching method for different students, and the student, after getting familiar with the teacher’s instruction mechanism, can infer the teacher’s intention to learn faster. Recently, the benefits of integrating this cooperative pedagogy into machine concept learning in discrete spaces have been proved by multiple works. However, how cooperative pedagogy can facilitate machine parameter learning hasn’t been thoroughly studied. In this paper, we propose a gradient optimization based teacher-aware learner who can incorporate teacher’s cooperative intention into the likelihood function and learn provably faster compared with the naive learning algorithms used in previous machine teaching works. We give theoretical proof that the iterative teacher-aware learning (ITAL) process leads to local and global improvements. We then validate our algorithms with extensive experiments on various tasks including regression, classification, and inverse reinforcement learning using synthetic and real data. We also show the advantage of modeling teacher-awareness when agents are learning from human teachers.

Author Information

Luyao Yuan (University of California, Los Angeles)
Dongruo Zhou (UCLA)
Junhong Shen (University of California, Los Angeles)
Jingdong Gao (University of California, Los Angeles)
Jeffrey L Chen (UCLA)
Quanquan Gu (UCLA)
Ying Nian Wu (University of California, Los Angeles)
Song-Chun Zhu (UCLA)

More from the Same Authors