Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks17 from public data
- 38
- Graph-Based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey37
A novel perspective on the functionality of graphs within RAG and their impact on enhancing performance across a wide range of graph-structured data is offered, along with a detailed breakdown of the roles that graphs play in RAG, covering database construction, algorithms, pipelines, and tasks.
- 37
- Loop Detection and Correction of 3D Laser-Based SLAM with Visual Information28
This paper introduces visual bags-of-words techniques for loop closure detection in the 3D laser-based SLAM and proves that the method can efficiently reduce motion accumulation errors and successfully ensure the real-time performance of loop closure correction.
- A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness12
This work extensively benchmarks spectral GNNs with a focus on the spectral perspective, demystifying them as spectral graph filters and implements the filters within a unified spectral-oriented framework with dedicated graph computations and efficient training schemes.
- Topology-monitorable Contrastive Learning on Dynamic Graphs12
The proposed IDOL, a novel contrastive learning framework for dynamic graph representation learning, conducts the graph propagation process based on a specially designed Personalized PageRank algorithm which can capture the topological changes incrementally and achieves a desired performance guarantee.
- A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks11
This work proposes SpikeGCL, a novel GCL framework to learn binarized 1-bit representations for graphs, making balanced trade-offs between efficiency and performance, and provides theoretical guarantees to demonstrate that SpikeGCL has comparable expressiveness with its full-precision counterparts.
- 10
- Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph Summarization5
STAR-RAG is proposed, a temporal GraphRAG framework that relies on two key ideas: building a time-aligned rule graph and conducting propagation on this graph to narrow the search space and prioritize semantically relevant, time-consistent evidence.
- FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation5
This work argues that a better contrastive scheme should be tailored to the characteristics of graph neural networks (e.g., neighborhood aggregation) and proposes a simple yet effective method named FastGCL, which has competitive classification performance and significant training speedup compared to existing state-of-the-art methods.
- 5
- Massively Parallel Single-Source SimRanks in $o(\log n)$ Rounds3
This is the first single-source SimRank algorithm in MPC that can overcome the Θ(log n) round complexity barrier with provable result accuracy, and is the first single-source SimRank algorithm in MPC that can overcome the Θ(log n) round complexity barrier with provable result accuracy.
- 1
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.