MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation

• URL: http://arxiv.org/abs/2606.22272v1
• Date: Sat, 20 Jun 2026 23:45:19 GMT
• Title: MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation
• Abstract summary: We present a novel strategy for unsupervised domain adaptation that combines custom PEFT architectures with mixed-objective training.<n>Our approach simultaneously optimize classification performance on labeled source domain data and masked language modeling (MLM) on unlabeled target domain data.
• Score: 1.7452931180966467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-trained language models struggle when applied to new domains, as full fine-tuning is computationally expensive and prone to catastrophic forgetting. This study addresses this challenge by presenting a novel parameter-efficient strategy for unsupervised domain adaptation that combines custom PEFT architectures with mixed-objective training. Our approach simultaneously optimizes classification performance on labeled source domain data and masked language modeling (MLM) on unlabeled target domain data, preserving target domain knowledge while adapting to source domain tasks. Our method employs a custom union of invertible adapters and Low-Rank Adaptation (LoRA) within a unified parameter-efficient framework. Through comprehensive evaluation on the Multi-Genre Natural Language Inference (MNLI) dataset across 20 domain shifts, our approach achieves significant improvements over existing methods: 1.41 percentage points over the current parameter-efficient state-of-the-art UDapter, 1.26 percentage points over the fully-tuned DANN baseline, and 0.86 percentage points over DSN, while utilizing only 7% of the model's trainable parameters. These results establish new benchmarks for parameter-efficient unsupervised domain adaptation and demonstrate that carefully designed PEFT combinations with concurrent optimization can outperform both existing parameter-efficient methods and traditional fully-tuned approaches.

Related papers

• BPG: Balancing Plasticity and Generalization for Domain Incremental Learning [48.68747632195046]
  Domain incremental learning enables models to continuously adapt while retaining prior knowledge.<n>We propose BPG, a unified framework that addresses both challenges through two complementary components.<n>BPG consistently outperforms uniform adapter-based approaches and hard domain selection strategies.
  arXiv  Detail & Related papers  (2026-08-11T11:22:27Z)
• Tunable Domain Adaptation Using Unfolding [11.125968799758438]
  We propose two novel domain adaptation methods for regression tasks based on interpretable unrolled networks.<n>These models leverage the functional dependence of select tunable parameters on domain variables, enabling controlled adaptation during inference.<n>We validate our approach on compressed sensing problems involving noise-adaptive sparse signal recovery, domain-adaptive gain calibration, and domain-adaptive phase retrieval.
  arXiv  Detail & Related papers  (2026-03-27T19:15:05Z)
• Domain Adaptation via Feature Refinement [0.3867363075280543]
  We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift.<n>The proposed method combines three key components: adaptation of Batch Normalization statistics using unlabeled target data, feature distillation from a source-trained model and hypothesis transfer.
  arXiv  Detail & Related papers  (2025-08-22T06:32:19Z)
• DIDS: Domain Impact-aware Data Sampling for Large Language Model Training [61.10643823069603]
  We present Domain Impact-aware Data Sampling (DIDS) for large language models.<n>DIDS group training data based on learning effects, where a proxy language model and dimensionality reduction are employed.<n>It achieves 3.4% higher average performance while maintaining comparable training efficiency.
  arXiv  Detail & Related papers  (2025-04-17T13:09:38Z)
• Unsupervised Parameter Efficient Source-free Post-pretraining [52.27955794126508]
  We introduce UpStep, an Unsupervised.<n>Source-free post-pretraining approach to adapt a base model from a source domain to a target domain.<n>We use various general backbone architectures, both supervised and unsupervised, trained on Imagenet as our base model.
  arXiv  Detail & Related papers  (2025-02-28T18:54:51Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignment [7.991720491452191]
  Online Test-Time Adaptation (OTTA) has emerged as an effective strategy to handle distributional shifts. This paper introduces a novel cosine alignment optimization approach with a dual-objective loss function. Our method outperforms state-of-the-art techniques and sets a new benchmark in multiple datasets.
  arXiv  Detail & Related papers  (2024-05-12T05:57:37Z)
• Parameter-Efficient Fine-Tuning With Adapters [5.948206235442328]
  This research introduces a novel adaptation method utilizing the UniPELT framework as a base. Our method employs adapters, which enable efficient transfer of pretrained models to new tasks with minimal retraining of the base model parameters.
  arXiv  Detail & Related papers  (2024-05-09T01:40:38Z)
• Controllable Prompt Tuning For Balancing Group Distributional Robustness [53.336515056479705]
  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. We propose 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.
  arXiv  Detail & Related papers  (2024-03-05T06:23:55Z)
• Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation [86.02485817444216]
  We introduce Multi-Prompt Alignment (MPA), a simple yet efficient framework for multi-source UDA. MPA denoises the learned prompts through an auto-encoding process and aligns them by maximizing the agreement of all the reconstructed prompts. Experiments show that MPA achieves state-of-the-art results on three popular datasets with an impressive average accuracy of 54.1% on DomainNet.
  arXiv  Detail & Related papers  (2022-09-30T03:40:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.