REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning

• URL: http://arxiv.org/abs/2604.17257v2
• Date: Tue, 21 Apr 2026 06:47:04 GMT
• Title: REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning
• Abstract summary: Recent text models are often adapted to specialized domains via contrastive pre-finetuning (PFT) on a collection of scattered, heterogeneous tasks.<n>This approach often introduces task-induced bias alongside domain knowledge, leading to uncontrolled representation shifts.<n>We propose R, a representation regularization framework that explicitly controls representation shift during embedding pre-finetuning.
• Score: 5.853890728403084
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent text embedding models are often adapted to specialized domains via contrastive pre-finetuning (PFT) on a naive collection of scattered, heterogeneous tasks. However, this approach often introduces task-induced bias alongside domain knowledge, leading to uncontrolled representation shifts that distort the pretrained embedding geometry and cause substantial performance degradation. To address this issue, we propose REZE, a representation regularization framework that explicitly controls representation shift during embedding pre-finetuning. REZE operates on the relations of anchor-positive pairs and decomposes them in an eigenspace. It then measures task-wise dispersion along each eigencomponent to identify task-variant directions and applies adaptive soft-shrinkage to suppress task-induced noise while preserving task-invariant semantic structure, without inference-time overhead. Experiments across multiple embedding backbones and specialized benchmarks show that REZE outperforms standard pre-finetuning and isotropy-oriented post-hoc regularization in most settings, remaining stable where existing PFT variants collapse. Embedding space analyses further confirm that REZE induces controlled shifts aligned with the original embedding manifold, underscoring representation shift control as a key principle for robust embedding pre-finetuning under heterogeneous supervision.

Related papers

• Multimodal Foundation Models Adaptation based on Domain-Aware Relaxed Orthogonal Subspace for Remote Sensing [16.45880716714667]
  Domain-aware Relaxed Orthogonal Subspace adaptation (DROS)<n>DROS reformulates low-rank adaptation as data-conditioned subspace learning and flexible subspace adaptation.<n>Experiments on multiple remote sensing benchmarks demonstrate that DROS achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-09-12T02:19:11Z)
• Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection [58.25418970608328]
  We study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains.<n>Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution.<n>We propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem.
  arXiv  Detail & Related papers  (2026-07-08T09:27:15Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting [64.2640656619583]
  Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-augmented prediction.<n>We propose a Retrieval-guided Invariant-Dynamic DEcomposition framework for time series forecasting.
  arXiv  Detail & Related papers  (2026-05-24T07:31:55Z)
• MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation [65.068801413044]
  Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams.<n>We introduce MoASE, a mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture.
  arXiv  Detail & Related papers  (2026-05-18T01:52:12Z)
• AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers [24.937985157569823]
  We argue that such timestep-agnostic alignment is suboptimal because the useful granularity of representation supervision changes systematically with the signal-to-noise ratio.<n>In high-noise regimes, diffusion models benefit more from coarse semantic and layout-level anchoring, whereas in low-noise regimes, the training signal should emphasize spatially detailed and structurally faithful refinement.<n>This non-stationary alignment behavior creates a representational mismatch for static single-level supervisors.
  arXiv  Detail & Related papers  (2026-05-05T03:07:29Z)
• Explicit Dropout: Deterministic Regularization for Transformer Architectures [55.09895958546215]
  Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through masking.<n>We propose a deterministic formulation that expresses dropout as an additive regularizer directly incorporated into the training loss.
  arXiv  Detail & Related papers  (2026-04-22T12:45:51Z)
• From Entanglement to Alignment: Representation Space Decomposition for Unsupervised Time Series Domain Adaptation [18.100665738436398]
  We introduce DARSD, a novel UDA framework with theoretical explainability that explicitly realizes UDA tasks from the perspective of representation space decomposition.<n>DarSD consists of three synergistic components: (I) An adversarial learnable common invariant basis that projects original features into a domain-invariant subspace while preserving semantic content; (II) A pseudo-labeling mechanism that dynamically separates target features based on confidence, hindering error accumulation; (III) A hybrid contrastive optimization strategy that simultaneously enforces feature clustering and consistency while mitigating emerging distribution gaps.
  arXiv  Detail & Related papers  (2025-07-28T16:26:28Z)
• On the Theory of Conditional Feature Alignment for Unsupervised Domain-Adaptive Counting [27.44207520673983]
  Object counting models suffer when deployed across domains with differing density variety.<n>We propose a theoretical framework of conditional feature alignment and provide a straightforward implementation.
  arXiv  Detail & Related papers  (2025-06-20T16:37:48Z)
• Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation [0.0]
  MAADA is a novel framework that decomposes adversarial perturbations into on-manifold and off-manifold components.<n>We show that MAADA consistently outperforms existing adversarial and adaptation methods in both unsupervised and few-shot settings.
  arXiv  Detail & Related papers  (2025-05-21T07:13:09Z)
• ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains [25.075869018443925]
  ReservoirTTA is a novel plug-in framework designed for prolonged test-time adaptation.<n>At its core, ReservoirTTA maintains a reservoir of domain-specialized models.<n>Our theoretical analysis reveals key components that bound parameter variance and prevent model collapse.
  arXiv  Detail & Related papers  (2025-05-20T15:39:20Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Debiased Fine-Tuning for Vision-language Models by Prompt Regularization [56.48290708901531]
  We present a new paradigm for fine-tuning large-scale vision pre-trained models on downstream task, dubbed Prompt Regularization (ProReg)<n>ProReg uses the prediction by prompting the pretrained model to regularize the fine-tuning.<n>We show the consistently strong performance of ProReg compared with conventional fine-tuning, zero-shot prompt, prompt tuning, and other state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-01-29T11:53:55Z)
• Posterior Differential Regularization with f-divergence for Improving Model Robustness [95.05725916287376]
  We focus on methods that regularize the model posterior difference between clean and noisy inputs. We generalize the posterior differential regularization to the family of $f$-divergences. Our experiments show that regularizing the posterior differential with $f$-divergence can result in well-improved model robustness.
  arXiv  Detail & Related papers  (2020-10-23T19:58:01Z)

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.