# Semantics Alignment via Split Learning for Resilient Multi-User Semantic Communication

arXiv: https://arxiv.org/abs/2310.09394 · HTML: https://mlsanity.com/paper/2310.09394/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 13 Oct 2023.

## Builds on (most cited first, 11 of 11)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [Semantic Communications: Principles and Challenges](https://mlsanity.com/paper/2201.01389/) (2021)
- [Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications](https://mlsanity.com/paper/2008.02608/) (2020)
- [Task-Oriented Multi-User Semantic Communications for VQA Task](https://mlsanity.com/paper/2108.07357/) (2021)
- [DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2206.08100/) (2022)
- [Semantics-Native Communication with Contextual Reasoning](https://mlsanity.com/paper/2108.05681/) (2021)
- [End-to-End Learning of Communications Systems Without a Channel Model](https://mlsanity.com/paper/1804.02276/) (2018)
- [Semantic Channel Equalizer: Modelling Language Mismatch in Multi-User Semantic Communications](https://mlsanity.com/paper/2308.03789/) (2023)

## Built on by (most cited first, 3 of 3)

- [Distillation-Enabled Knowledge Alignment Protocol for Semantic Communication in AI Agent Networks](https://mlsanity.com/paper/2505.17030/) (2025)
- [RIS-aided Latent Space Alignment for Semantic Channel Equalization](https://mlsanity.com/paper/2507.16450/) (2025)
- [Distillation-Enabled Knowledge Alignment for Generative Semantic Communications of AIGC Images](https://mlsanity.com/paper/2506.19893/) (2025)

## Abstract (arXiv)

Recent studies on semantic communication commonly rely on neural network (NN) based transceivers such as deep joint source and channel coding (DeepJSCC). Unlike traditional transceivers, these neural transceivers are trainable using actual source data and channels, enabling them to extract and communicate semantics. On the flip side, each neural transceiver is inherently biased towards specific source data and channels, making different transceivers difficult to understand intended semantics, particularly upon their initial encounter. To align semantics over multiple neural transceivers, we propose a distributed learning based solution, which leverages split learning (SL) and partial NN fine-tuning techniques. In this method, referred to as SL with layer freezing (SLF), each encoder downloads a misaligned decoder, and locally fine-tunes a fraction of these encoder-decoder NN layers. By adjusting this fraction, SLF controls computing and communication costs. Simulation results confirm the effectiveness of SLF in aligning semantics under different source data and channel dissimilarities, in terms of classification accuracy, reconstruction errors, and recovery time for comprehending intended semantics from misalignment.