VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty

Randy Ardywibowo · Zepeng Huo · Zhangyang “Atlas” Wang · Bobak Mortazavi · Shuai Huang · Xiaoning Qian

Hall E #519

Keywords: [ PM: Bayesian Models and Methods ] [ MISC: General Machine Learning Techniques ]

[ Abstract ]
[ Poster [ Paper PDF
Wed 20 Jul 3:30 p.m. PDT — 5:30 p.m. PDT
Spotlight presentation: MISC: General Machine Learning Techniques
Wed 20 Jul 7:30 a.m. PDT — 9 a.m. PDT


Continual Learning (CL) is the problem of sequentially learning a set of tasks and preserving all the knowledge acquired. Many existing methods assume that the data stream is explicitly divided into a sequence of known contexts (tasks), and use this information to know when to transfer knowledge from one context to another. Unfortunately, many real-world CL scenarios have no clear task nor context boundaries, motivating the study of task-agnostic CL, where neither the specific tasks nor their switches are known both in training and testing. This paper proposes a variational architecture growing framework dubbed VariGrow. By interpreting dynamically growing neural networks as a Bayesian approximation, and defining flexible implicit variational distributions, VariGrow detects if a new task is arriving through an energy-based novelty score. If the novelty score is high and the sample is detected" as a new task, VariGrow will grow a new expert module to be responsible for it. Otherwise, the sample will be assigned to one of the existing experts who is mostfamiliar" with it (i.e., one with the lowest novelty score). We have tested VariGrow on several CIFAR and ImageNet-based benchmarks for the strict task-agnostic CL setting and demonstrate its consistent superior performance. Perhaps surprisingly, its performance can even be competitive compared to task-aware methods.

Chat is not available.