Paper Detail

KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models

Phuong Tuan Dat, Phuong Khai Minh, Tran Huy Dat

arxiv Score 20.0

Published 2026-09-04 · First seen 2026-09-09

Research Track A

Abstract

Fully fine-tuning self-supervised learning (SSL) speech models for downstream tasks is computationally prohibitive, and existing parameter-efficient fine-tuning approaches predominantly rely on MLP-based adapters whose fixed activation functions limit their representational expressiveness under tight parameter budgets. We propose \textbf{KanAdapter}, a lightweight adapter framework that replaces conventional MLP bottlenecks with Group-Rational Kolmogorov-Arnold Network (GR-KAN) modules for more expressive and parameter-efficient adaptation. Following a parallel bottleneck design, KanAdapter inserts trainable GR-KAN branches alongside frozen Transformer encoder blocks and leverages weight transfer from pre-trained MLP layers for stable initialization. Across speaker verification, speech emotion recognition, and deepfake detection, KanAdapter achieves up to 97.5\% reduction in trainable parameters relative to full fine-tuning while remaining highly competitive, and consistently outperforms AdaptFormer under comparable parameter budgets. In continual learning, it yields up to 83.6\% error reduction over full fine-tuning and MLP-based adapters, which we attribute to the localized nature of GR-KAN's rational activations that mitigates catastrophic forgetting. To our knowledge, this is the first work to explore KAN-based modules for parameter-efficient fine-tuning of speech foundation models.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{dat2026kanadapter,
  title = {KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models},
  author = {Phuong Tuan Dat and Phuong Khai Minh and Tran Huy Dat},
  year = {2026},
  abstract = {Fully fine-tuning self-supervised learning (SSL) speech models for downstream tasks is computationally prohibitive, and existing parameter-efficient fine-tuning approaches predominantly rely on MLP-based adapters whose fixed activation functions limit their representational expressiveness under tight parameter budgets. We propose \textbackslash{}textbf\{KanAdapter\}, a lightweight adapter framework that replaces conventional MLP bottlenecks with Group-Rational Kolmogorov-Arnold Network (GR-KAN) modules for more },
  url = {https://arxiv.org/abs/2609.05281},
  keywords = {cs.SD},
  eprint = {2609.05281},
  archiveprefix = {arXiv},
}

Metadata

{}