Timezone: »
Machine teaching addresses the problem of finding the best training data that can guide a learning algorithm to a target model with minimal effort. In conventional settings, a teacher provides data that are consistent with the true data distribution. However, for sequential learners which actively choose their queries, such as multi-armed bandits and active learners, the teacher can only provide responses to the learner’s queries, not design the full data. In this setting, consistent teachers can be sub-optimal for finite horizons. We formulate this sequential teaching problem, which current techniques in machine teaching do not address, as a Markov decision process, with the dynamics nesting a model of the learner and the actions being the teacher's responses. Furthermore, we address the complementary problem of learning from a teacher that plans: to recognise the teaching intent of the responses, the learner is endowed with a model of the teacher. We test the formulation with multi-armed bandit learners in simulated experiments and a user study. The results show that learning is improved by (i) planning teaching and (ii) the learner having a model of the teacher. The approach gives tools to taking into account strategic (planning) behaviour of users of interactive intelligent systems, such as recommendation engines, by considering them as boundedly optimal teachers.
Author Information
Tomi Peltola (Aalto University)
Mustafa Mert Çelikok (Aalto University)
Pedram Daee (Aalto University)
Samuel Kaski (Aalto University)
More from the Same Authors
-
2021 Poster: De-randomizing MCMC dynamics with the diffusion Stein operator »
Zheyang Shen · Markus Heinonen · Samuel Kaski -
2020 Poster: Rethinking pooling in graph neural networks »
Diego Mesquita · Amauri Souza · Samuel Kaski -
2018 : Modelling User's Theory of AI's Mind in Interactive Intelligent Systems »
Tomi Peltola -
2017 Poster: Non-Stationary Spectral Kernels »
Sami Remes · Markus Heinonen · Samuel Kaski -
2017 Poster: Differentially private Bayesian learning on distributed data »
Mikko Heikkilä · Eemil Lagerspetz · Samuel Kaski · Kana Shimizu · Sasu Tarkoma · Antti Honkela -
2014 Workshop: Machine Learning in Computational Biology »
Oliver Stegle · Sara Mostafavi · Anna Goldenberg · Su-In Lee · Michael Leung · Anshul Kundaje · Mark B Gerstein · Martin Renqiang Min · Hannes Bretschneider · Francesco Paolo Casale · Loïc Schwaller · Amit G Deshwar · Benjamin A Logsdon · Yuanyang Zhang · Ali Punjani · Derek C Aguiar · Samuel Kaski