Timezone: »

 
Mixture of Basis for Interpretable Continual Learning with Distribution Shifts
Mengda Xu · Sumitra Ganesh · Pranay Pasula
Event URL: https://openreview.net/forum?id=Jqzzko0IdSB »
Continual learning in environments with shifting data distributions is a challenging problem with several real-world applications. In this paper we consider settings in which the data distribution (task) shifts abruptly and the timing of these shifts are not known. Furthermore, we consider a $\textit{semi-supervised task-agnostic}$ setting in which the learning algorithm has access to both task-segmented and unsegmented data for offline training. We propose a new approach for this problem setting - Mixture of Basis models (MoB). The core idea is to learn a small set of basis models and construct a dynamic, task-dependent mixture of the models to predict for the current task. We also propose a new methodology to detect observations that are out-of-distribution with respect to the existing basis models and instantiate new models. We test our approach in multiple domains and show that it achieves better prediction error compared to existing methods in most cases, while using fewer models. Moreover, we analyze the latent task representations learned by MoB to show that similar tasks tend to cluster together in the latent space and that the latent representation shifts at the task boundaries when the tasks are dissimilar.

Author Information

Mengda Xu (Columbia University)
Sumitra Ganesh (JPMorgan - AI Research)
Pranay Pasula (J.P. Morgan AI Research)

More from the Same Authors

  • 2022 Poster: ASPiRe: Adaptive Skill Priors for Reinforcement Learning »
    Mengda Xu · Manuela Veloso · Shuran Song
  • 2021 Poster: Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs »
    Thomas Spooner · Nelson Vadori · Sumitra Ganesh
  • 2020 : 25 - Complex Skill Acquisition through Simple Skill Imitation Learning »
    Pranay Pasula
  • 2020 Poster: Calibration of Shared Equilibria in General Sum Partially Observable Markov Games »
    Nelson Vadori · Sumitra Ganesh · Prashant Reddy · Manuela Veloso
  • 2019 : Poster Session »
    Nathalie Baracaldo · Seth Neel · Tuyen Le · Dan Philps · Suheng Tao · Sotirios Chatzis · Toyo Suzumura · Wei Wang · WENHANG BAO · Solon Barocas · Manish Raghavan · Samuel Maina · Reginald Bryant · Kush Varshney · Skyler D. Speakman · Navdeep Gill · Nicholas Schmidt · Kevin Compher · Naveen Sundar Govindarajulu · Vivek Sharma · Praneeth Vepakomma · Tristan Swedish · Jayashree Kalpathy-Cramer · Ramesh Raskar · Shihao Zheng · Mykola Pechenizkiy · Marco Schreyer · Li Ling · Chirag Nagpal · Robert Tillman · Manuela Veloso · Hanjie Chen · Xintong Wang · Michael Wellman · Matthew van Adelsberg · Ben Wood · Hans Buehler · Mahmoud Mahfouz · Antonios Alexos · Megan Shearer · Antigoni Polychroniadou · Lucia Larise Stavarache · Dmitry Efimov · Johnston P Hall · Yukun Zhang · Emily Diana · Sumitra Ganesh · Vineeth Ravi · · Swetasudha Panda · Xavier Renard · Matthew Jagielski · Yonadav Shavit · Joshua Williams · Haoran Wei · Shuang (Sophie) Zhai · Xinyi Li · Hongda Shen · Daiki Matsunaga · Jaesik Choi · Alexis Laignelet · Batuhan Guler · Jacobo Roa Vicens · Ajit Desai · Jonathan Aigrain · Robert Samoilescu