Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control (2401.12624v2)
Abstract: In this work, we compare emergent communication (EC) built upon multi-agent deep reinforcement learning (MADRL) and language-oriented semantic communication (LSC) empowered by a pre-trained LLM using human language. In a multi-agent remote navigation task, with multimodal input data comprising location and channel maps, it is shown that EC incurs high training cost and struggles when using multimodal data, whereas LSC yields high inference computing cost due to the LLM's large size. To address their respective bottlenecks, we propose a novel framework of language-guided EC (LEC) by guiding the EC training using LSC via knowledge distillation (KD). Simulations corroborate that LEC achieves faster travel time while avoiding areas with poor channel conditions, as well as speeding up the MADRL training convergence by up to 61.8% compared to EC.
- D. Gündüz, Z. Qin, I. E. Aguerri, H. S. Dhillon, Z. Yang, A. Yener, K. K. Wong, and C. B. Chae, “Beyond transmitting bits: Context, semantics, and task-oriented communications,” IEEE Journal on Selected Areas in Communications, vol. 41, pp. 5 – 41, 2023.
- E. Bourtsoulatze, D. B. Kurka, and D. Gündüz, “Deep joint source-channel coding for wireless image transmission,” IEEE Transactions on Cognitive Communications and Networking, vol. 5, pp. 567 – 579, 2019.
- J. N. Foerster, Y. M. Assael, N. D. Freitas, and S. Whiteson, “Learning to communicate with deep multi-agent reinforcement learning,” Neural Information Processing Systems, p. 2137–2145, 2016.
- S. Seo, J. Park, S.-W. Ko, J. Choi, M. Bennis, and S.-L. Kim, “Towards semantic communication protocols: A probabilistic logic perspective,” IEEE Journal on Selected Areas in Communications, 2023.
- H. Touvron et al., “Llama 2: Open foundation and fine-tuned chat models,” arXiv:2307.09288, 2023.
- J. Li, D. Li, C. Xiong, and S. Hoi, “BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation,” International Conference on Machine Learning, p. 12888–12900, 2022.
- H. Nam, J. Park, J. Choi, M. Bennis, and S. L. Kim, “Language-oriented communication with semantic coding and knowledge distillation for text-to-image generation,” arXiv:2309.11127, 2023.
- J. Huang and K. C. C. Chang, “Towards reasoning in large language models: A survey,” arXiv:2212.10403, 2022.
- H. Sha et al., “LanguageMPC: Large language models as decision makers for autonomous driving,” arXiv:2310.03026, 2023.
- G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” Proc. of NIPS Deep Learning Wksp., (Montre‘al, Canada), 2014.
- H. Jiang, “A latent space theory for emergent abilities in large language models,” arXiv:2304.09960, 2023.
- N. Wang, J. Xie, H. Luo, Q. Cheng, J. Wu, M. Jia, and L. Li, “Efficient image captioning for edge devices,” arXiv:2212.08985, 2022.
- X. Ye. (2023) calflops: a flops and params calculate tool for neural networks in pytorch framework. [Online]. Available: https://github.com/MrYxJ/calculate-flops.pytorch
- H. Choi, J. Oh, J. Chung, G. C. Alexandropoulos, and J. Choi, “WiThRay: A versatile ray-tracing simulator for smart wireless environments,” IEEE Access, vol. 11, pp. 56 822–56 845, 2023.
- E. Frantar, S. Ashkboos, T. Hoefler, and D. Alistarh, “GPTQ: Accurate post-training quantization for generative pre-trained transformers,” arXiv:2210.17323, 2022.