Pith. sign in

REVIEW 1 cited by

Controllable Prompt Tuning For Balancing Group Distributional Robustness

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 2403.02695 v2 pith:WLEIALMN submitted 2024-03-05 cs.LG

classification cs.LG
keywords performancegoodgroupsachieveacrosscontrollabledataintroduce
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Models trained on data composed of different groups or domains can suffer from severe performance degradation under distribution shifts. While recent methods have largely focused on optimizing the worst-group objective, this often comes at the expense of good performance on other groups. To address this problem, we introduce an optimization scheme to achieve good performance across groups and find a good solution for all without severely sacrificing performance on any of them. However, directly applying such optimization involves updating the parameters of the entire network, making it both computationally expensive and challenging. Thus, we introduce Controllable Prompt Tuning (CPT), which couples our approach with prompt-tuning techniques. On spurious correlation benchmarks, our procedures achieve state-of-the-art results across both transformer and non-transformer architectures, as well as unimodal and multimodal data, while requiring only 0.4% tunable parameters.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bridging Domain Adaptation and Graph Neural Networks: A Tensor-Based Framework for Effective Label Propagation

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A tensor-based GNN with pseudo-label-conditioned label propagation achieves state-of-the-art average accuracy on domain adaptive graph classification benchmarks.

Pith tools