Zero-shot Task Preference Addressing Enabled by Imprecise Bayesian Continual Learning
share
Like generic multi-task learning, continual learning has the nature of multi-objective optimization, and therefore faces a trade-off between the performance of different tasks. That is, to optimize for the current task distribution, it may need to compromise performance on some tasks to improve on others. This means there exist multiple models that are each optimal at different times, each addressing a distinct task-performance trade-off. Researchers have discussed how to train particular models to address specific preferences on these trade-offs. However, existing algorithms require additional sample overheads – a large burden when there are multiple, possibly infinitely many, preferences. As a response, we propose Imprecise Bayesian Continual Learning (IBCL). Upon a new task, IBCL (1) updates a knowledge base in the form of a convex hull of model parameter distributions and (2) obtains particular models to address preferences with zero-shot. That is, IBCL does not require any additional training overhead to construct preference-addressing models from its knowledge base. We show that models obtained by IBCL have guarantees in identifying the preferred parameters. Moreover, experiments show that IBCL is able to locate the Pareto set of parameters given a preference, maintain similar to better performance than baseline methods, and significantly reduce training overhead via zero-shot preference addressing.
READ FULL TEXT