Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Yan, Zuoyu"'
Cycles are fundamental elements in graph-structured data and have demonstrated their effectiveness in enhancing graph learning models. To encode such information into a graph learning framework, prior works often extract a summary quantity, ranging f
Externí odkaz:
http://arxiv.org/abs/2311.14333
We investigate the enhancement of graph neural networks' (GNNs) representation power through their ability in substructure counting. Recent advances have seen the adoption of subgraph GNNs, which partition an input graph into numerous subgraphs, subs
Externí odkaz:
http://arxiv.org/abs/2303.10576
Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent homology summaries remains slow for large and dense graphs and can be a
Externí odkaz:
http://arxiv.org/abs/2201.12032
In recent years, algebraic topology and its modern development, the theory of persistent homology, has shown great potential in graph representation learning. In this paper, based on the mathematics of algebraic topology, we propose a novel solution
Externí odkaz:
http://arxiv.org/abs/2110.02510
Publikováno v:
In Alexandria Engineering Journal November 2024 107:390-405
Encoder-decoder models have made great progress on handwritten mathematical expression recognition recently. However, it is still a challenge for existing methods to assign attention to image features accurately. Moreover, those encoder-decoder model
Externí odkaz:
http://arxiv.org/abs/2105.02412
Math expressions are important parts of scientific and educational documents, but some of them may be challenging for junior scholars or students to understand. Nevertheless, constructing textual descriptions for math expressions is nontrivial. In th
Externí odkaz:
http://arxiv.org/abs/2104.11890
Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encode
Externí odkaz:
http://arxiv.org/abs/2102.10255
Despite the recent advances in optical character recognition (OCR), mathematical expressions still face a great challenge to recognize due to their two-dimensional graphical layout. In this paper, we propose a convolutional sequence modeling network,
Externí odkaz:
http://arxiv.org/abs/2012.12619
Publikováno v:
In Colloids and Surfaces A: Physicochemical and Engineering Aspects 5 November 2022 652