相关论文: Visual FUDGE: Form Understanding via Dynamic Graph…

This paper studies the discovery of approximate rules in property graphs. We propose a semantically meaningful measure of error for mining graph entity dependencies (GEDs) at almost hold, to tolerate errors and inconsistencies that exist in…

The ability to detect edges is a fundamental attribute necessary to truly capture visual concepts. In this paper, we prove that edges cannot be represented properly in the first convolutional layer of a neural network, and further show that…

Entity-aware image captioning aims to describe named entities and events related to the image by utilizing the background knowledge in the associated article. This task remains challenging as it is difficult to learn the association between…

We make the case for language models over logical forms (LFLMs), arguing that such models are more data-efficient than their textual counterparts. To that end, we introduce the Graph-based Formal-Logical Distributional Semantics (GFoLDS)…

Infrared and visible image fusion aims to extract complementary features to synthesize a single fused image. Many methods employ convolutional neural networks (CNNs) to extract local features due to its translation invariance and locality.…

Despite their large-scale coverage, cross-domain knowledge graphs invariably suffer from inherent incompleteness and sparsity. Link prediction can alleviate this by inferring a target entity, given a source entity and a query relation.…

Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and…

We present a graph theory-based method to characterise flow defects and structural shifts in condensed matter. We explore the connection between dynamical properties, particularly the recently introduced concept of ''softness'', and…

Previous studies such as VizWiz find that Visual Question Answering (VQA) systems that can read and reason about text in images are useful in application areas such as assisting visually-impaired people. TextVQA is a VQA dataset geared…

Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning. Inspired by the success of graph convolutional networks (GCN) in…

Data heterogeneity across clients is a key challenge in federated learning. Prior works address this by either aligning client and server models or using control variates to correct client model drift. Although these methods achieve fast…

Knowledge graph embedding plays an important role in knowledge representation, reasoning, and data mining applications. However, for multiple cross-domain knowledge graphs, state-of-the-art embedding models cannot make full use of the data…

External knowledge,e.g., entities and entity descriptions, can help humans understand texts. Many works have been explored to include external knowledge in the pre-trained models. These methods, generally, design pre-training tasks and…

Textual-edge Graphs (TEGs), characterized by rich text annotations on edges, are increasingly significant in network science due to their ability to capture rich contextual information among entities. Existing works have proposed various…

Graphs are versatile tools for representing structured data. As a result, a variety of machine learning methods have been studied for graph data analysis. Although many such learning methods depend on the measurement of differences between…

Learning-based methods have become increasingly popular for solving vehicle routing problems due to their near-optimal performance and fast inference speed. Among them, the combination of deep reinforcement learning and graph representation…

Current research in form understanding predominantly relies on large pre-trained language models, necessitating extensive data for pre-training. However, the importance of layout structure (i.e., the spatial relationship between the entity…

Knowledge graphs, on top of entities and their relationships, contain other important elements: literals. Literals encode interesting properties (e.g. the height) of entities that are not captured by links between entities alone. Most of…

Recent studies successfully learned static graph embeddings that are structurally fair by preventing the effectiveness disparity of high- and low-degree vertex groups in downstream graph mining tasks. However, achieving structure fairness…

This paper studies learning on text-attributed graphs (TAGs), where each node is associated with a text description. An ideal solution for such a problem would be integrating both the text and graph structure information with large language…