Zobrazeno 1 - 10
of 795
pro vyhledávání: '"FENG, ZHUO"'
State-of-the-art hypergraph partitioners utilize a multilevel paradigm to construct progressively coarser hypergraphs across multiple layers, guiding cut refinements at each level of the hierarchy. Traditionally, these partitioners employ heuristic m
Externí odkaz:
http://arxiv.org/abs/2410.10875
SGM-PINN is a graph-based importance sampling framework to improve the training efficacy of Physics-Informed Neural Networks (PINNs) on parameterized problems. By applying a graph decomposition scheme to an undirected Probabilistic Graphical Model (P
Externí odkaz:
http://arxiv.org/abs/2407.07358
This paper presents a spectral framework for assessing the generalization and stability of Graph Neural Networks (GNNs) by introducing a Graph Geodesic Distance (GGD) metric. For two different graphs with the same number of nodes, our framework lever
Externí odkaz:
http://arxiv.org/abs/2406.10500
Autor:
Rosset, Corby, Chung, Ho-Lam, Qin, Guanghui, Chau, Ethan C., Feng, Zhuo, Awadallah, Ahmed, Neville, Jennifer, Rao, Nikhil
Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 and HotpotQA mainly study ``known unknowns'' with clear indications of
Externí odkaz:
http://arxiv.org/abs/2402.17896
Autor:
Aghdaei, Ali, Feng, Zhuo
This work presents inGRASS, a novel algorithm designed for incremental spectral sparsification of large undirected graphs. The proposed inGRASS algorithm is highly scalable and parallel-friendly, having a nearly-linear time complexity for the setup p
Externí odkaz:
http://arxiv.org/abs/2402.16990
Modern graph neural networks (GNNs) can be sensitive to changes in the input graph structure and node features, potentially resulting in unpredictable behavior and degraded performance. In this work, we introduce a spectral framework known as SAGMAN
Externí odkaz:
http://arxiv.org/abs/2402.08653
Continual learning on graphs tackles the problem of training a graph neural network (GNN) where graph data arrive in a streaming fashion and the model tends to forget knowledge from previous tasks when updating with new data. Traditional continual le
Externí odkaz:
http://arxiv.org/abs/2401.03077
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2022 Aug 15
This work introduces a highly-scalable spectral graph densification framework (SGL) for learning resistor networks with linear measurements, such as node voltages and currents. We show that the proposed graph learning approach is equivalent to solvin
Externí odkaz:
http://arxiv.org/abs/2302.04384
Autor:
Feng, Zhuo1 (AUTHOR) fz2187941887@163.com, Shi, Kaichuang1,2 (AUTHOR) shikaichuang@126.com, Yin, Yanwen2 (AUTHOR) fsp166@163.com, Shi, Yuwen1 (AUTHOR) shb2009@gxu.edu.cn, Feng, Shuping2 (AUTHOR) longfeng1136@163.com, Long, Feng2 (AUTHOR), Wei, Zuzhang1 (AUTHOR) shikaichuang@126.com, Si, Hongbin1 (AUTHOR)
Publikováno v:
Animals (2076-2615). Dec2024, Vol. 14 Issue 23, p3551. 16p.
