GraphUniverse: Synthetic Graph Generation for Evaluating Inductive Generalization
A fundamental challenge in graph learning is understanding how models generalize to new, unseen graphs. While synthetic benchmarks offer controlled settings for analysis, existing approaches are confined to single-graph, transductive settings where models train and test on the same graph structure. Addressing this gap, we introduce GraphUniverse, a framework for generating entire families of graphs to enable the first systematic evaluation of inductive generalization at scale. Our core innovation is the generation of graphs with persistent semantic communities, ensuring conceptual consistency while allowing fine-grained control over structural properties like homophily and degree distributions. This enables crucial but underexplored robustness tests, such as performance under controlled distribution shifts. Benchmarking a wide range of architectures -- from GNNs to graph transformers and topological architectures -- reveals that strong transductive performance is a poor predictor of inductive generalization. Furthermore, we find that robustness to distribution shift is highly sensitive not only to model architecture choice but also to the initial graph regime (e.g., high vs. low homophily). Beyond benchmarking, GraphUniverse's flexibility and scalability can facilitate the development of robust and truly generalizable architectures. The framework is open-source at https://github.com/LouisVanLangendonck/GraphUniverse.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph GenerationGraph LearningSimilar Papers 제목 키워드 기반
Graph Condensation for Inductive Node Representation Learning
Graph neural networks (GNNs) encounter significant computational challenges when handling large-scale graphs, which severely restricts their efficacy across diverse applications. To address this limitation, graph condens…
Representation LearningAn Open Challenge for Inductive Link Prediction on Knowledge Graphs
An emerging trend in representation learning over knowledge graphs (KGs) moves beyond transductive link prediction tasks over a fixed set of known entities in favor of inductive tasks that imply training on one graph and…
Graph Representation LearningInductive Link PredictionKnowledge GraphsLink Prediction+1What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the discovery of Newtonian mechanics. Howev…
Inductive BiasCase2Code: Learning Inductive Reasoning with Synthetic Data
Complex reasoning is an impressive ability shown by large language models (LLMs). Most LLMs are skilled in deductive reasoning, such as chain-of-thought prompting or iterative tool-using to solve challenging tasks step-b…
Synthesizing Diverse Network Flow Datasets with Scalable Dynamic Multigraph Generation
Obtaining real-world network datasets is often challenging because of privacy, security, and computational constraints. In the absence of such datasets, graph generative models become essential tools for creating synthet…
DiversityGenerative Adversarial NetworkGraph Generation