Related papers: Weakly Supervised Concept Map Generation through T…
Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might…
Data efficiency, or the ability to generalize from a few labeled data, remains a major challenge in deep learning. Semi-supervised learning has thrived in traditional recognition tasks alleviating the need for large amounts of labeled data,…
In this paper, we introduce a self-supervised learning method to enhance the graph-level representations with the help of a set of subgraphs. For this purpose, we propose a universal framework to generate subgraphs in an auto-regressive way…
Dynamic Text-Attributed Graphs (DyTAGs), which intricately integrate structural, temporal, and textual attributes, are crucial for modeling complex real-world systems. However, most existing DyTAG datasets exhibit poor textual quality,…
Knowledge Graph (KG)-to-Text Generation has seen recent improvements in generating fluent and informative sentences which describe a given KG. As KGs are widespread across multiple domains and contain important entity-relation information,…
Subgraph representation learning has emerged as an important problem, but it is by default approached with specialized graph neural networks on a large global graph. These models demand extensive memory and computational resources but…
Conceptual Graphs (CGs) are a formalism to represent knowledge. However producing a CG database is complex. To the best of our knowledge, existing methods do not fully use the expressivity of CGs. It is particularly troublesome as it is…
Most available data is unstructured, making it challenging to access valuable information. Automatically building Knowledge Graphs (KGs) is crucial for structuring data and making it accessible, allowing users to search for information…
Generating patent descriptions from scientific papers is challenging due to fundamental rhetorical and structural disparities between the two genres. Existing approaches treat this as surface-level rewriting, failing to capture the…
The Artificial Intelligence industry regularly develops applications that mostly rely on Knowledge Bases, a data repository about specific, or general, domains, usually represented in a graph shape. Similar to other databases, they face two…
Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the…
Data-to-text (D2T) generation aims to transform structured data into natural language text. Data-to-text pre-training has proved to be powerful in enhancing D2T generation and yields impressive performances. However, previous pre-training…
Graph translation is very promising research direction and has a wide range of potential real-world applications. Graph is a natural structure for representing relationship and interactions, and its translation can encode the intrinsic…
In this paper, we approach an overlooked yet critical task Graph2Image: generating images from multimodal attributed graphs (MMAGs). This task poses significant challenges due to the explosion in graph size, dependencies among graph…
Recent research has demonstrated the efficacy of pre-training graph neural networks (GNNs) to capture the transferable graph semantics and enhance the performance of various downstream tasks. However, the semantic knowledge learned from…
Text-Attributed Graphs (TAGs) enhance graph structures with natural language descriptions, enabling detailed representation of data and their relationships across a broad spectrum of real-world scenarios. Despite the potential for deeper…
Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately. However, existing methods…
Incorporating external graph knowledge into neural chatbot models has been proven effective for enhancing dialogue generation. However, in conventional graph neural networks (GNNs), message passing on a graph is independent from text,…
We propose a weakly supervised approach for creating maps using free-form textual descriptions. We refer to this work of creating textual maps as zero-shot mapping. Prior works have approached mapping tasks by developing models that predict…
Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. However, training GNNs usually requires abundant task-specific labeled data, which is often arduously expensive to obtain. One effective…