How Expressive are Knowledge Graph Foundation Models?

• URL: http://arxiv.org/abs/2502.13339v1
• Date: Tue, 18 Feb 2025 23:38:39 GMT
• Title: How Expressive are Knowledge Graph Foundation Models?
• Authors: Xingyue Huang, Pablo Barceló, Michael M. Bronstein, İsmail İlkan Ceylan, Mikhail Galkin, Juan L Reutter, Miguel Romero Orth,
• Abstract summary: We show that the expressive power of Knowledge Graph Foundation Models directly depends on the motifs that are used to learn the relation representations. As part of our study, we design more expressive KGFMs using richer motifs, which necessitate learning relation representations based on, e.g., how triples of relations interact with each other.
• Score: 29.718081334595542
• License:
• Abstract: Knowledge Graph Foundation Models (KGFMs) are at the frontier for deep learning on knowledge graphs (KGs), as they can generalize to completely novel knowledge graphs with different relational vocabularies. Despite their empirical success, our theoretical understanding of KGFMs remains very limited. In this paper, we conduct a rigorous study of the expressive power of KGFMs. Specifically, we show that the expressive power of KGFMs directly depends on the motifs that are used to learn the relation representations. We then observe that the most typical motifs used in the existing literature are binary, as the representations are learned based on how pairs of relations interact, which limits the model's expressiveness. As part of our study, we design more expressive KGFMs using richer motifs, which necessitate learning relation representations based on, e.g., how triples of relations interact with each other. Finally, we empirically validate our theoretical findings, showing that the use of richer motifs results in better performance on a wide range of datasets drawn from different domains.

Related papers

• Graph Stochastic Neural Process for Inductive Few-shot Knowledge Graph Completion [63.68647582680998]
  We focus on a task called inductive few-shot knowledge graph completion (I-FKGC) Inspired by the idea of inductive reasoning, we cast I-FKGC as an inductive reasoning problem. We present a neural process-based hypothesis extractor that models the joint distribution of hypothesis, from which we can sample a hypothesis for predictions. In the second module, based on the hypothesis, we propose a graph attention-based predictor to test if the triple in the query set aligns with the extracted hypothesis.
  arXiv  Detail & Related papers  (2024-08-03T13:37:40Z)
• zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models [33.10218179341504]
  We use large language models to generate relation representations for embedding-based TKGF methods. We show that our approach helps TKGF models to achieve much better performance in forecasting the facts with previously unseen relations.
  arXiv  Detail & Related papers  (2023-11-15T21:25:15Z)
• Visual Commonsense based Heterogeneous Graph Contrastive Learning [79.22206720896664]
  We propose a heterogeneous graph contrastive learning method to better finish the visual reasoning task. Our method is designed as a plug-and-play way, so that it can be quickly and easily combined with a wide range of representative methods.
  arXiv  Detail & Related papers  (2023-11-11T12:01:18Z)
• Towards Foundation Models for Knowledge Graph Reasoning [18.77355708537997]
  Knowledge graphs (KGs) have different entity and relation vocabularies that generally do not overlap. We present ULTRA, an approach for learning universal and transferable graph representations. We find that the zero-shot inductive inference performance of a single pre-trained ULTRA model on unseen graphs of various sizes is often on par or better than strong baselines trained on specific graphs.
  arXiv  Detail & Related papers  (2023-10-06T20:00:07Z)
• Knowledge Graph Embedding: An Overview [42.16033541753744]
  We make a comprehensive overview of the current state of research in Knowledge Graph completion. We focus on two main branches of KG embedding (KGE) design: 1) distance-based methods and 2) semantic matching-based methods. Next, we delve into CompoundE and CompoundE3D, which draw inspiration from 2D and 3D affine operations.
  arXiv  Detail & Related papers  (2023-09-21T21:52:42Z)
• Probing Graph Representations [77.7361299039905]
  We use a probing framework to quantify the amount of meaningful information captured in graph representations. Our findings on molecular datasets show the potential of probing for understanding the inductive biases of graph-based models. We advocate for probing as a useful diagnostic tool for evaluating graph-based models.
  arXiv  Detail & Related papers  (2023-03-07T14:58:18Z)
• I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning [16.723470319188102]
  Knowledge graph embedding seeks to learn vector representations for entities and relations. Recent studies have used pre-trained language models to learn embeddings based on the textual information of entities and relations. We propose CoLE, a Co-distillation Learning method for KG Embedding that exploits the complement of graph structures and text information.
  arXiv  Detail & Related papers  (2022-08-21T07:34:37Z)
• Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis [96.53859361560505]
  We propose a knowledge graph augmented network (KGAN) to incorporate external knowledge with explicitly syntactic and contextual information. KGAN captures the sentiment feature representations from multiple perspectives, i.e., context-, syntax- and knowledge-based. Experiments on three popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN.
  arXiv  Detail & Related papers  (2022-01-13T08:25:53Z)
• What is Learned in Knowledge Graph Embeddings? [3.224929252256631]
  A knowledge graph (KG) is a data structure which represents entities and relations as the vertices and edges of a directed graph with edge types. We investigate whether learning rules between relations is indeed what drives the performance of embedding-based methods. Using experiments on synthetic KGs, we show that KG models can learn motifs and how this ability is degraded by non-motif edges.
  arXiv  Detail & Related papers  (2021-10-19T13:52:11Z)
• RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding [50.010601631982425]
  This paper extends the random walk model (Arora et al., 2016a) of word embeddings to Knowledge Graph Embeddings (KGEs) We derive a scoring function that evaluates the strength of a relation R between two entities h (head) and t (tail) We propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph.
  arXiv  Detail & Related papers  (2021-01-25T13:31:29Z)
• Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction [84.64435075778988]
  We propose a general approach to learn relation prototypes from unlabeled texts. We learn relation prototypes as an implicit factor between entities. We conduct experiments on two publicly available datasets: New York Times and Google Distant Supervision.
  arXiv  Detail & Related papers  (2020-11-27T06:21:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.