Skip to content
Preprint

AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning

Jul 2026 · 1 citation · 39 references
Computer Science

TL;DR

AE-PSL is proposed, a communication-efficient PSL framework that compresses intermediate activations and gradients using a lightweight AutoEncoder placed at the split layer and introduces a novel two-stage alignment mechanism, which adapts the AE to the pre-trained model's feature manifold and client-specific feature distributions before DFT.

Abstract

Distributed Fine-Tuning (DFT) of large-scale Foundation Models (FMs) on resource-constrained edge devices is limited by local compute constraints and communication overhead. Parallel Split Learning (PSL) reduces client-side computation by keeping few model layers on each client and offloading the remaining computation to the server; however, clients must exchange intermediate activations and gradients with the server at every training step. Existing SL communication-compression methods mainly rely on task-agnostic heuristics, such as sparsification and quantization. While learnable SL compressors can better adapt to intermediate representations, they require co-training with the target model. Therefore, directly inserting them into off-the-shelf FMs introduces feature-distribution misalignment and degrades DFT performance. To address this, we propose AE-PSL, a communication-efficient PSL framework that compresses intermediate activations and gradients using a lightweight AutoEncoder (AE) placed at the split layer. To ensure compatibility of AE compression with pre-trained FMs, AE-PSL introduces a novel two-stage alignment mechanism, which adapts the AE to the pre-trained model's feature manifold and client-specific feature distributions before DFT.

View source

Similar papers

Preprint Aug 2026

SplitLite: Low-Rank Residual Compression for Split Learning

SplitLite is proposed, a communication-efficient split federated LoRA fine-tuning method that exploits the low effective rank structure of consecutive-epoch activation and gradient residuals, thereby significantly reducing both activation uplink and gradient downlink traffic.

Tao Li, Yulin Tang, Qi Guo et al. · 0 citations
Preprint Aug 2026

DeaMoE: Efficient MoE Structure for Fast Small-Batch Decoding

DeaMoE is proposed, a decoding-efficient MoE architecture, in which the experts are grouped into several departments, and the experts belonging to the same department share most parameters since they come from the same professional field, and additionally each expert contains a few private parameters to reflect its uniqueness.

Zewen Jin, Shengyu Fu, Zeping Duan et al. · 0 citations
Book Open access Aug 2026

Towards Network-Efficient Cross-Regional Inference via Learned Activation Compression

Feather is presented, a system that reduces this overhead by compressing intermediate activations before transmission and reconstructing them before downstream layers resume execution, consistently outperforming existing compression schemes, including linear autoencoder, PCA, and SVD.

Regan McDonald, M. Rego, Ertza Warraich et al. · 0 citations
Aug 2026

EP-MAE: A resource-efficient masked autoencoding framework for 3D neural representation learning.

Efficient Point Masked Autoencoders (EP-MAE), a new framework designed to significantly reduce the training cost of 3D self-supervised pre-training while maintaining strong representation quality, and provides a scalable and effective foundation for future 3D neural network models is presented.

Jian Zhu, Jiale Zhao, Cheng Lin et al. · 0 citations
Jul 2026

P4Q: Learning to Prompt for Quantization in Low-Bit CLIP

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated remarkable performance across various visual and multimodal tasks. However, deploying these models on downstream application platforms remains challenging due to computational demands and domain gaps. Quantization offers a promising solution by significantly reducing these costs, making VLMs more feasible for deployment in such environments. There are two prevailing paradigms: Quantization-Aware Training (QAT), which preserves model performance but incurs substantial training costs; and Post-Training Quantization (PTQ), which offers greater efficiency but introduces multimodal gaps and leads to performance degradation on downstream tasks. To reduce computational costs and bridge domain gaps, we propose the “Prompt for Quantization” (P4Q) by integrating PTQ with Parameter-Efficient Fine-Tuning (PEFT) techniques. P4Q compresses model parameters and activations via PTQ, introducing learnable prompts and low-bit adapters to enhance performance on downstream tasks. The learnable prompts embed downstream knowledge to mitigate domain gaps, while the low-bit adapters realign the distributions of image and text features, thereby mitigating multimodal gaps. We also introduce a distillation loss based on cosine similarity predictions to distill the quantized model using a full-precision teacher model. Extensive experiments on thirteen datasets demonstrate that P4Q significantly enhances the performance of low-bit CLIP while reducing deployment costs. For instance, an 8-bit P4Q compressed CLIP-ViT/B-32 achieves 66.94% Top-1 accuracy on ImageNet, surpassing the prompt fine-tuned full-precision counterpart by 2.24% while reducing model size by 4 \(\times\) . The source code is publicly available at https://github.com/HuixinSun/P4Q_official.

H. Sun, Runqi Wang, Yanjing Li et al. · 0 citations
Preprint Jul 2026

MixCompress: Mixture of Experts for Variable Rate Learned Image Compression

This work proposes MixCompress, a unified VBR framework based on sparse structural specialization that not only matches individually optimized single-rate baselines but can even surpass them, establishing a new Pareto frontier for computationally efficient image coding.

Calvin-Khang Ta, Praneet Singh, Tong Shao et al. · 0 citations