Related papers: Doc-GCN: Heterogeneous Graph Convolutional Network…

Analyzing the layout of a document to identify headers, sections, tables, figures etc. is critical to understanding its content. Deep learning based approaches for detecting the layout structure of document images have been promising.…

Due to the development of graph neural networks, graph-based representation learning methods have made great progress in recommender systems. However, data sparsity is still a challenging problem that most graph-based recommendation methods…

An undirected weighted graph (UWG) is frequently adopted to describe the interactions among a solo set of nodes from real applications, such as the user contact frequency from a social network services system. A graph convolutional network…

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the…

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-based methods to aggregate information, i.e., manually…

Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures have emerged -- transformer-based models inspired by LLMs,…

Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG).…

Multi-label node classification is an important yet under-explored domain in graph mining as many real-world nodes belong to multiple categories rather than just a single one. Although a few efforts have been made by utilizing Graph…

Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art performance and has attracted considerable attention. Current deep…

Document layout analysis has a wide range of requirements across various domains, languages, and business scenarios. However, most current state-of-the-art algorithms are language-dependent, with architectures that rely on transformer…

Digital data is a gold mine for modern journalism. However, datasets which interest journalists are extremely heterogeneous, ranging from highly structured (relational databases), semi-structured (JSON, XML, HTML), graphs (e.g., RDF), and…

Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word…

In this paper, we propose the Graph-Learning-Dual Graph Convolutional Neural Network called GLDGCN based on the classic Graph Convolutional Neural Network(GCN) by introducing dual convolutional layer and graph learning layer. We apply…

Recently, Graph Convolutional Networks (GCNs) and their variants have been receiving many research interests for learning graph-related tasks. While the GCNs have been successfully applied to this problem, some caveats inherited from…

Graph Convolutional Networks (GCNs) are powerful models for node representation learning tasks. However, the node representation in existing GCN models is usually generated by performing recursive neighborhood aggregation across multiple…

Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks. These works tend to sample and group points to create smaller point sets locally and mainly focus on extracting…

Graph Convolutional Network (GCN) are widely used in Graph Anomaly Detection (GAD) due to their natural compatibility with graph structures, resulting in significant performance improvements. However, most researchers approach GAD as a…

The distance-geometric graph representation adopts a unified scheme (distance) for representing the geometry of three-dimensional(3D) graphs. It is invariant to rotation and translation of the graph and it reflects pair-wise node…

The objective of image manipulation detection is to identify and locate the manipulated regions in the images. Recent approaches mostly adopt the sophisticated Convolutional Neural Networks (CNNs) to capture the tampering artifacts left in…

Graph Neural Networks (GNNs) have drawn tremendous attention due to their unique capability to extend Machine Learning (ML) approaches to applications broadly-defined as having unstructured data, especially graphs. Compared with other…