23 citations · 47 across the 11 of their papers we have counts for
11 papers
GraphPL: Leveraging GNN for Efficient and Robust Modalities Imputation in Patchwork Learning
Xingjian Hu, Zuoyu Yan, Jianhua Zhu +3
Current research on distributed multi-modal learning typically assumes that clients can access complete information across all modalities, which may not hold in practice. In this p…
Enhancing Graph Representation Learning with Localized Topological Features
Zuoyu Yan, Qi Zhao, Ze Ye +5
Representation learning on graphs is a fundamental problem that can be crucial in various tasks. Graph neural networks, the dominant approach for graph representation learning, are…
Cycle Invariant Positional Encoding for Graph Representation Learning
Zuoyu Yan, Tengfei Ma, Liangcai Gao +3
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 learn…
An Efficient Subgraph GNN with Provable Substructure Counting Power
Zuoyu Yan, Junru Zhou, Liangcai Gao +2
We investigate the enhancement of graph neural networks' (GNNs) representation power through their ability in substructure counting. Recent advances have seen the adoption of subgr…
Neural Approximation of Graph Topological Features
Zuoyu Yan, Tengfei Ma, Liangcai Gao +3
Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent ho…
Cycle Representation Learning for Inductive Relation Prediction
Zuoyu Yan, Tengfei Ma, Liangcai Gao +2
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…
Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer
Wenqi Zhao, Liangcai Gao, Zuoyu Yan +3
Encoder-decoder models have made great progress on handwritten mathematical expression recognition recently. However, it is still a challenge for existing methods to assign attenti…
Automatic Description Construction for Math Expression via Topic Relation Graph
Ke Yuan, Zuoyu Yan, Yibo Li +2
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, const…
Link Prediction with Persistent Homology: An Interactive View
Zuoyu Yan, Tengfei Ma, Liangcai Gao +2
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…
ConvMath: A Convolutional Sequence Network for Mathematical Expression Recognition
Zuoyu Yan, Xiaode Zhang, Liangcai Gao +2
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…
Preliminary Exploration of Formula Embedding for Mathematical Information Retrieval: can mathematical formulae be embedded like a natural language?
Liangcai Gao, Zhuoren Jiang, Yue Yin +3
While neural network approaches are achieving breakthrough performance in the natural language related fields, there have been few similar attempts at mathematical language related…