# Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems

arXiv: https://arxiv.org/abs/2507.01035 · HTML: https://mlsanity.com/paper/2507.01035/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Compact Language Models via Pruning and Knowledge Distillation](https://mlsanity.com/paper/2407.14679/) (2024)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference](https://mlsanity.com/paper/2210.08803/) (2022)
- [Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks](https://mlsanity.com/paper/2403.05185/) (2024)
- [LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics](https://mlsanity.com/paper/2209.14065/) (2022)
- [Low-latency Mini-batch GNN Inference on CPU-FPGA Heterogeneous Platform](https://mlsanity.com/paper/2206.08536/) (2022)
- [Reforge: Low-Latency Distributed GNN Serving with Selective Embedding Recomputation](https://mlsanity.com/paper/2501.08547/) (2025)
- [A Novel Evaluation Perspective on GNNs-based Recommender Systems through the Topology of the User-Item Graph](https://mlsanity.com/paper/2408.11762/) (2024)

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

- [Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM](https://mlsanity.com/paper/2509.13179/) (2025)
- [Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users](https://mlsanity.com/paper/2509.09066/) (2025)

## Abstract (arXiv)

The incessant advent of online services demands high speed and efficient recommender systems (ReS) that can maintain real-time performance along with processing very complex user-item interactions. The present study, therefore, considers computational bottlenecks involved in hybrid Graph Neural Network (GNN) and Large Language Model (LLM)-based ReS with the aim optimizing their inference latency and training efficiency. An extensive methodology was used: hybrid GNN-LLM integrated architecture-optimization strategies(quantization, LoRA, distillation)-hardware acceleration (FPGA, DeepSpeed)-all under R 4.4.2. Experimental improvements were significant, with the optimal Hybrid + FPGA + DeepSpeed configuration reaching 13.6% more accuracy (NDCG@10: 0.75) at 40-60ms of latency, while LoRA brought down training time by 66% (3.8 hours) in comparison to the non-optimized baseline. Irrespective of domain, such as accuracy or efficiency, it can be established that hardware-software co-design and parameter-efficient tuning permit hybrid models to outperform GNN or LLM approaches implemented independently. It recommends the use of FPGA as well as LoRA for real-time deployment. Future work should involve federated learning along with advanced fusion architectures for better scalability and privacy preservation. Thus, this research marks the fundamental groundwork concerning next-generation ReS balancing low-latency response with cutting-edge personalization.