paper-with-me

Papers

SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache

2025-05-16 · Qiuyu Zhu, Liang Zhang, Qianxiong Xu, Cheng Long, Jie Zhang

Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning. We observe that for different queries, it could retrieve similar subgraphs as prompts, and thus we propose SubGCache, which aims to reduce inference latency by reusing computation across queries with similar structural prompts (i.e., subgraphs). Specifically, SubGCache clusters queries based on subgraph embeddings, constructs a representative subgraph for each cluster, and pre-computes the key-value (KV) cache of the representative subgraph. For each query with its retrieved subgraph within a cluster, it reuses the pre-computed KV cache of the representative subgraph of the cluster without computing the KV tensors again for saving computation. Experiments on two new datasets across multiple LLM backbones and graph-based RAG frameworks demonstrate that SubGCache consistently reduces inference latency with comparable and even improved generation quality, achieving up to 6.68$\times$ reduction in time-to-first-token (TTFT).

📄 PDF Abstract BibTeX arXiv:2505.10951

Code (0)

등록된 구현이 없습니다.

Tasks

RAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
WordPiece 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

CDFGNN: a Systematic Design of Cache-based Distributed Full-Batch Graph Neural Network Training with Communication Reduction

2024-08-01 · Shuai Zhang, Zite Jiang, Haihang You

Graph neural network training is mainly categorized into mini-batch and full-batch training methods. The mini-batch training method samples subgraphs from the original graph in each iteration. This sampling operation int…

Graph Neural NetworkQuantization

AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs

2023-05-27 · Yangjie Zhou, Yaoxu Song, Jingwen Leng, Zihan Liu 외

Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features. As such, achieving high-performance execution for GNNs becomes crucially important. Prior works have proposed…

BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing

2021-12-16 · Tianfeng Liu, Yangrui Chen, Dan Li, Chuan Wu 외

Graph neural networks (GNNs) have extended the success of deep neural networks (DNNs) to non-Euclidean graph data, achieving ground-breaking performance on various tasks such as node classification and graph property pre…

GPUGraph Property PredictionNode ClassificationProperty Prediction

OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models

2026-06-30 · Huanlin Gao, Fang Zhao, Qiang Hui, Fuyuan Shi 외 arxiv

We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives,…

GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures

2026-02-03 · Yikang Yang, Zhengxin Yang, Minghao Luo, Luzhou Peng 외 arxiv

Finding frequently occurring subgraph patterns or network motifs in neural architectures is crucial for optimizing efficiency, accelerating design, and uncovering structural insights. However, as the subgraph size increa…