LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915744298565632 |
|---|---|
| author | Liu, Chenyu Li, Haige Rossi, Luca |
| author_facet | Liu, Chenyu Li, Haige Rossi, Luca |
| contents | Graph Neural Networks (GNNs) are neural networks that aim to process graph data, capturing the relationships and interactions between nodes using the message-passing mechanism. GNN quantization has emerged as a promising approach for reducing model size and accelerating inference in resource-constrained environments. Compared to quantization in LLMs, quantizing graph features is more emphasized in GNNs. Inspired by the above, we propose to leverage prompt learning, which manipulates the input data, to improve the performance of quantization-aware training (QAT) for GNNs. To mitigate the issue that prompting the node features alone can only make part of the quantized aggregation result optimal, we introduce Low-Rank Aggregation Prompting (LoRAP), which injects lightweight, input-dependent prompts into each aggregated feature to optimize the results of quantized aggregations. Extensive evaluations on 4 leading QAT frameworks over 9 graph datasets demonstrate that LoRAP consistently enhances the performance of low-bit quantized GNNs while introducing a minimal computational overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15079 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training Liu, Chenyu Li, Haige Rossi, Luca Machine Learning Social and Information Networks Graph Neural Networks (GNNs) are neural networks that aim to process graph data, capturing the relationships and interactions between nodes using the message-passing mechanism. GNN quantization has emerged as a promising approach for reducing model size and accelerating inference in resource-constrained environments. Compared to quantization in LLMs, quantizing graph features is more emphasized in GNNs. Inspired by the above, we propose to leverage prompt learning, which manipulates the input data, to improve the performance of quantization-aware training (QAT) for GNNs. To mitigate the issue that prompting the node features alone can only make part of the quantized aggregation result optimal, we introduce Low-Rank Aggregation Prompting (LoRAP), which injects lightweight, input-dependent prompts into each aggregated feature to optimize the results of quantized aggregations. Extensive evaluations on 4 leading QAT frameworks over 9 graph datasets demonstrate that LoRAP consistently enhances the performance of low-bit quantized GNNs while introducing a minimal computational overhead. |
| title | LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2601.15079 |