DBScholar

Back to papers

DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention

Summary: Dependency attention: graph-aware attention that prunes token-pair interactions to structural dependencies and reuses computations along relational paths to reduce inference cost. DepCache: KV-cache reuse aligned across graph-augmented prompts with a locality-aware replacement policy, yielding 1.5–5× throughput and up to 3.2× time-to-first-token reduction without accuracy loss. (summarized by gpt-5-mini on Feb 11 2026)

Paper ID
7564
Venue
SIGMOD
Year
2026
Pagerank
5.093636e-05
Overall Rank
10,357 | 28.95%
DOI
10.1145/3769778

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@inproceedings{yuan_sigmod26,
        title = {{DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention}},
        author = {Yuan, Hao and Ai, Xin and Wang, Qiange and Li, Peizheng and Yu, Jiayang and Chen, Chaoyi and Yang, Xinbo and Zhang, Yanfeng and Fu, Zhenbo and Wen, Yingyou and Yu, Ge},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3769778},
        url = {https://dl.acm.org/doi/10.1145/3769778},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 9 of 9 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
2,233 FINEdex: A Fine-grained Learned Index Scheme for Scalable and Concurrent Memory Systems 2022 VLDB 8.8968964e-05
2,695 NeutronStar: Distributed GNN Training with Hybrid Dependency Management 2022 SIGMOD 8.2468134e-05
2,816 Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation 2025 SIGMOD 8.0959781e-05
4,430 PQCache: Product Quantization-based KVCache for Long Context LLM Inference 2025 SIGMOD 6.7091071e-05
5,316 Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective 2024 VLDB 6.2687017e-05
6,806 HongTu: Scalable Full-Graph GNN Training on Multiple GPUs 2023 SIGMOD 5.7673207e-05
7,906 Buffered Persistence in B+ Trees 2024 SIGMOD 5.5181056e-05
9,546 NeutronTP: Load-Balanced Distributed Full-Graph GNN Training with Tensor Parallelism 2025 VLDB 5.2528121e-05
13,309 NeutronRAG: Towards Understanding the Effectiveness of RAG from a Data Retrieval Perspective 2025 SIGMOD -
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 6,900 Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving 2025 SIGMOD
2 6,254 In-depth Analysis of Graph-based RAG in a Unified Framework 2025 VLDB
3 13,291 OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration 2026 VLDB
4 6,432 RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference 2026 VLDB
5 13,340 ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models 2025 VLDB
6 6,788 HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems 2026 SIGMOD
7 4,430 PQCache: Product Quantization-based KVCache for Long Context LLM Inference 2025 SIGMOD
8 10,459 From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation 2026 SIGMOD
9 10,259 KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference 2026 SIGMOD
10 2,816 Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation 2025 SIGMOD