# Distillation-Enabled Knowledge Alignment Protocol for Semantic Communication in AI Agent Networks

arXiv: https://arxiv.org/abs/2505.17030 · HTML: https://mlsanity.com/paper/2505.17030/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 7 May 2025.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [The Expressive Power of Low-Rank Adaptation](https://mlsanity.com/paper/2310.17513/) (2023)
- [Deep Learning-Enabled Semantic Communication Systems with Task-Unaware Transmitter and Dynamic Data](https://mlsanity.com/paper/2205.00271/) (2022)
- [Semantic Channel Equalizer: Modelling Language Mismatch in Multi-User Semantic Communications](https://mlsanity.com/paper/2308.03789/) (2023)
- [Dynamic Relative Representations for Goal-Oriented Semantic Communications](https://mlsanity.com/paper/2403.16986/) (2024)
- [Semantics Alignment via Split Learning for Resilient Multi-User Semantic Communication](https://mlsanity.com/paper/2310.09394/) (2023)
- [Soft Partitioning of Latent Space for Semantic Channel Equalization](https://mlsanity.com/paper/2405.20085/) (2024)
- [Zero-Forget Preservation of Semantic Communication Alignment in Distributed AI Networks](https://mlsanity.com/paper/2411.19385/) (2024)

## Built on by (most cited first, 2 of 2)

- [Distillation-Enabled Knowledge Alignment for Generative Semantic Communications of AIGC Images](https://mlsanity.com/paper/2506.19893/) (2025)
- [Token Encoding for Semantic Recovery](https://mlsanity.com/paper/2604.12931/) (2026)

## Abstract (arXiv)

Future networks are envisioned to connect massive artificial intelligence (AI) agents, enabling their extensive collaboration on diverse tasks. Compared to traditional entities, these agents naturally suit the semantic communication (SC), which can significantly enhance the bandwidth efficiency. Nevertheless, SC requires the knowledge among agents to be aligned, while agents have distinct expert knowledge for their individual tasks in practice. In this paper, we propose a distillation-enabled knowledge alignment protocol (DeKAP), which distills the expert knowledge of each agent into parameter-efficient low-rank matrices, allocates them across the network, and allows agents to simultaneously maintain aligned knowledge for multiple tasks. We formulate the joint minimization of alignment loss, communication overhead, and storage cost as a large-scale integer linear programming problem and develop a highly efficient greedy algorithm. From computer simulation, the DeKAP establishes knowledge alignment with the lowest communication and computation resources compared to conventional approaches.