Pith. sign in

REVIEW

DynaShare: Task and Instance Conditioned Parameter Sharing for Multi-Task Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.17305 v1 pith:66UKDZ2U submitted 2023-05-26 cs.CV

classification cs.CV
keywords sharingparameterinferencemulti-tasktaskacrossapproachduring
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Multi-task networks rely on effective parameter sharing to achieve robust generalization across tasks. In this paper, we present a novel parameter sharing method for multi-task learning that conditions parameter sharing on both the task and the intermediate feature representations at inference time. In contrast to traditional parameter sharing approaches, which fix or learn a deterministic sharing pattern during training and apply the same pattern to all examples during inference, we propose to dynamically decide which parts of the network to activate based on both the task and the input instance. Our approach learns a hierarchical gating policy consisting of a task-specific policy for coarse layer selection and gating units for individual input instances, which work together to determine the execution path at inference time. Experiments on the NYU v2, Cityscapes and MIMIC-III datasets demonstrate the potential of the proposed approach and its applicability across problem domains.

Discussion (0). Continue with ORCID to comment.

Pith tools