paper-with-me

홈 › Papers

GraphUniverse: Synthetic Graph Generation for Evaluating Inductive Generalization

2025-09-25 · Louis Van Langendonck, Guillermo Bernárdez, Nina Miolane, Pere Barlet-Ros arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.21097

Code (0)

등록된 구현이 없습니다.

Tasks

Graph GenerationGraph Learning

Similar Papers 제목 키워드 기반

Graph Condensation for Inductive Node Representation Learning

2023-07-29 · Xinyi Gao, Tong Chen, Yilong Zang, Wentao Zhang 외

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 Learning

An Open Challenge for Inductive Link Prediction on Knowledge Graphs

2022-03-03 · Mikhail Galkin, Max Berrendorf, Charles Tapley Hoyt

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+1

What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models

2025-07-09 · Keyon Vafa, Peter G. Chang, Ashesh Rambachan, Sendhil Mullainathan

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 Bias

Case2Code: Learning Inductive Reasoning with Synthetic Data

2024-07-17 · Yunfan Shao, Linyang Li, Yichuan Ma, Peiji Li 외

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

2025-05-12 · Arya Grayeli, Vipin Swarup, Steven E. Noel

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