Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever

• URL: http://arxiv.org/abs/2509.16508v1
• Date: Sat, 20 Sep 2025 03:07:03 GMT
• Title: Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever
• Authors: Marijan Fofonjka, Shahryar Zehtabi, Alireza Behtash, Tyler Mauer, David Stout,
• Abstract summary: We propose a novel encoder in which token embeddings of a new corpus learn to produce enhanced soft embeddings for it, while requiring less compute power to update than full finetuning.<n>We adopt federated learning (FL) and differential privacy (DP) to achieve an efficient, privacy-constrained, and product-grade training solution.
• Score: 0.6524460254566904
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: When existing retrieval-augmented generation (RAG) solutions are intended to be used for new knowledge domains, it is necessary to update their encoders, which are taken to be pretrained large language models (LLMs). However, fully finetuning these large models is compute- and memory-intensive, and even infeasible when deployed on resource-constrained edge devices. We propose a novel encoder architecture in this work that addresses this limitation by using a frozen small language model (SLM), which satisfies the memory constraints of edge devices, and inserting a small adapter network before the transformer blocks of the SLM. The trainable adapter takes the token embeddings of the new corpus and learns to produce enhanced soft embeddings for it, while requiring significantly less compute power to update than full fine-tuning. We further propose a novel retrieval mechanism by attaching a classifier head to the SLM encoder, which is trained to learn a similarity mapping of the input embeddings to their corresponding documents. Finally, to enable the online fine-tuning of both (i) the encoder soft embeddings and (ii) the classifier-as-retriever on edge devices, we adopt federated learning (FL) and differential privacy (DP) to achieve an efficient, privacy-preserving, and product-grade training solution. We conduct a theoretical analysis of our methodology, establishing convergence guarantees under mild assumptions on gradient variance when deployed for general smooth nonconvex loss functions. Through extensive numerical experiments, we demonstrate (i) the efficacy of obtaining soft embeddings to enhance the encoder, (ii) training a classifier to improve the retriever, and (iii) the role of FL in achieving speedup.

Related papers

• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning [91.90342432541138]
  Scaling up model size and training data has advanced foundation models for instance-level perception.<n>High computational cost limits adoption on resource-constrained platforms.<n>We introduce a new benchmark for efficient segmentation on both high-performance computing platforms and mobile devices.
  arXiv  Detail & Related papers  (2025-10-16T18:00:00Z)
• OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case [0.0]
  This paper presents a mathematically rigorous framework for autoencoder-type deep neural networks.<n>It yields memory-efficient training and automated architecture discovery.<n>The framework's utility is illustrated with application to image denoising and deblurring tasks.
  arXiv  Detail & Related papers  (2025-09-09T22:11:33Z)
• EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning [53.88000987041739]
  Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time.<n>We propose the Elastic Knowledge Preservation and Compensation (EKPC) method, integrating Importance-aware importance Regularization (IPR) and Trainable Semantic Drift Compensation (TSDC) for CIL.
  arXiv  Detail & Related papers  (2025-06-14T05:19:58Z)
• SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices [38.27552394580526]
  Dynamic nature of data, characterized by continuous changes or data drift, poses significant challenges for on-device machine learning models.<n>Traditional centralized approach to continual learning is unsuitable for end devices due to privacy and data volume concerns.<n>FCL emerges as a promising solution, preserving user data locally while enhancing models through collaborative updates.
  arXiv  Detail & Related papers  (2025-05-01T07:26:35Z)
• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks [81.2624272756733]
  In dense retrieval, deep encoders provide embeddings for both inputs and targets. We train a small parametric corrector network that adjusts stale cached target embeddings. Our approach matches state-of-the-art results even when no target embedding updates are made during training.
  arXiv  Detail & Related papers  (2024-09-03T13:29:13Z)
• Online Adaptation of Language Models with a Memory of Amortized Contexts [82.02369596879817]
  Memory of Amortized Contexts (MAC) is an efficient and effective online adaptation framework for large language models. We show how MAC can be combined with and improve the performance of popular alternatives such as retrieval augmented generations.
  arXiv  Detail & Related papers  (2024-03-07T08:34:57Z)
• Dynamic Encoding and Decoding of Information for Split Learning in Mobile-Edge Computing: Leveraging Information Bottleneck Theory [1.1151919978983582]
  Split learning is a privacy-preserving distributed learning paradigm in which an ML model is split into two parts (i.e., an encoder and a decoder) In mobile-edge computing, network functions can be trained via split learning where an encoder resides in a user equipment (UE) and a decoder resides in the edge network. We present a new framework and training mechanism to enable a dynamic balancing of the transmission resource consumption with the informativeness of the shared latent representations.
  arXiv  Detail & Related papers  (2023-09-06T07:04:37Z)
• Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design [18.675244280002428]
  We propose a novel FL framework named coded federated learning (SCFL) that leverages coded computing techniques. In SCFL, each edge device uploads a privacy-preserving coded dataset to the server, which is generated by adding noise to the projected local dataset. We show that SCFL learns a better model within the given time and achieves a better privacy-performance tradeoff than the baseline methods.
  arXiv  Detail & Related papers  (2022-11-08T09:58:36Z)
• Tiny Machine Learning for Concept Drift [8.452237741722726]
  This paper introduces a Tiny Machine Learning for Concept Drift (TML-CD) solution based on deep learning feature extractors and a k-nearest neighbors. The adaptation module continuously updates the knowledge base of TML-CD to deal with concept drift affecting the data-generating process. The porting of TML-CD on three off-the-shelf micro-controller units shows the feasibility of what is proposed in real-world pervasive systems.
  arXiv  Detail & Related papers  (2021-07-30T17:02:04Z)
• Fast-Convergent Federated Learning [82.32029953209542]
  Federated learning is a promising solution for distributing machine learning tasks through modern networks of mobile devices. We propose a fast-convergent federated learning algorithm, called FOLB, which performs intelligent sampling of devices in each round of model training.
  arXiv  Detail & Related papers  (2020-07-26T14:37:51Z)

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.