Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks16 from public data
- SCARA41
This work proposes SCARA, a scalable GNN with feature-oriented optimization for graph computation, which achieves sub-linear time complexity with a guaranteed precision in propagation process as well as GNN training and inference.
- Achieving adversarial robustness via sparsity21
This work theoretically prove that the sparsity of network weights is closely associated with model robustness, and proposes a novel adversarial training method called inverse weights inheritance, which imposes sparse weights distribution on a large network by inheriting weights from a small network, thereby improving the robustness of the large network.
- Scalable decoupling graph neural network with feature-oriented optimization20
Theoretical analysis indicates that the proposed SCARA model achieves sub-linear time complexity with a guaranteed precision in propagation process as well as GNN training and inference, and is efficient to process precomputation on the largest available billion-scale GNN dataset Papers100M.
- SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation17
SIGMA is proposed, an efficient global heterophilous GNN aggregation integrating the structural similarity measurement SimRank that inherently captures distant global similarity even under heterophily, that conventional approaches can only achieve after iterative aggregations.
- Machine Learning for Subgraph Extraction: Methods, Applications and Challenges17
This tutorial discusses learning-based approaches for four well known subgraph problems, namely subgraph isomorphism, maximum common subgraph, community detection and community search problems, and gives a general description of each model, and analyse its design and performance.
- 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.
- GENTI: GPU-Powered Walk-Based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs11
This work proposes GENTI, a GPU-oriented SGRL algorithm for dynamic graphs that improves the critical subgraph extraction stage by disentangling it into two phases, namely neighbor sampling and subgraph gathering, which are respectively performed on CPU and GPU in an asynchronous fashion.
- RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU8
RAGDoll is introduced, a resource-efficient, self-adaptive RAG serving system integrated with LLMs, specifically designed for resource-constrained platforms and achieves up to 3.6 times speedup in average latency compared to serial RAG systems based on vLLM.
- 4
- 4
- HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling3
This work tackles the GT scalability issue by proposing HubGT, which is boosted by decoupled graph computation and hierarchical graph representations, which offers efficient computation and mini-batch capability over existing GT designs on large-scale datasets while achieving top-tier effectiveness.
- Advances in Designing Scalable Graph Neural Networks: The Perspective of Graph Data Management3
This primer tutorial aims to provide a comprehensive overview of scalable GNN designs, highlighting the most recent and prominent models that focus on the scalability issue, and summarize the technical challenges and suggest potential future directions regarding the rapid developments in this field.
- DHIL-GT: Scalable Graph Transformer with Decoupled Hierarchy Labeling2
DHIL-GT effectively retrieves hierarchical information by exploiting the graph labeling technique, as it shows that the graph label hierarchy is more informative than plain adjacency by offering global connections while promoting locality, and is particularly suitable for handling complex graph patterns such as heterophily.
- –
- –
- –
Publication data from OpenAlex; 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.