Related papers: Towards Graph Foundation Models: Training on Knowl…
Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation.…
Currently, Deep Learning (DL) components within a Case-Based Reasoning (CBR) application often lack the comprehensive integration of available domain knowledge. The trend within machine learning towards so-called Informed machine learning…
Knowledge graphs have emerged as a popular method for injecting up-to-date, factual knowledge into large language models (LLMs). This is typically achieved by converting the knowledge graph into text that the LLM can process in context.…
Many complex real-world systems exhibit inherently intertwined temporal and spatial characteristics. Spatio-temporal knowledge graphs (STKGs) have therefore emerged as a powerful representation paradigm, as they integrate entities,…
Multimodal knowledge graphs (MKGs), which intuitively organize information in various modalities, can benefit multiple practical downstream tasks, such as recommendation systems, and visual question answering. However, most MKGs are still…
Graph foundation models (GFM) aim to acquire transferable knowledge by pre-training on diverse graphs, which can be adapted to various downstream tasks. However, domain shift in graphs is inherently two-dimensional: graphs differ not only…
Graphs are a central representation in biomedical research, capturing molecular interaction networks, gene regulatory circuits, cell--cell communication maps, and knowledge graphs. Despite their importance, currently there is not a broadly…
This paper focuses on learning representation on the whole graph level in an unsupervised manner. Learning graph-level representation plays an important role in a variety of real-world issues such as molecule property prediction, protein…
The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets. However, extending…
Large Language Models (LLMs) show strong reasoning ability in open-domain question answering, yet their reasoning processes are typically linear and often logically inconsistent. In contrast, real-world reasoning requires integrating…
Knowledge graphs can represent information about the real-world using entities and their relations in a structured and semantically rich manner and they enable a variety of downstream applications such as question-answering, recommendation…
The construction of Generalized Knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these…
Self-play reinforcement learning has shown strong performance in domains with formally verifiable structure, such as mathematics and coding, where both problem generation and reward computation can be grounded in explicit rules. Extending…
In this paper we consider the task of conversational semantic parsing over general purpose knowledge graphs (KGs) with millions of entities, and thousands of relation-types. We focus on models which are capable of interactively mapping user…
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG,…
The goal of knowledge graph completion (KGC) is to predict missing links in a KG using trained facts that are already known. In recent, pre-trained language model (PLM) based methods that utilize both textual and structural information are…
Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains.…
Session search involves a series of interactive queries and actions to fulfill user's complex information need. Current strategies typically prioritize sequential modeling for deep semantic understanding, overlooking the graph structure in…
Structural knowledge graph foundation models aim to generalize reasoning to completely new graphs with unseen entities and relations. A key limitation of existing approaches like Ultra is their reliance on a single relational transformation…
In this study, we focus on the graph representation learning (a.k.a. network embedding) in attributed graphs. Different from existing embedding methods that treat the incorporation of graph structure and semantic as the simple combination…