# Fully-inductive Node Classification on Arbitrary Graphs

arXiv: https://arxiv.org/abs/2405.20445 · HTML: https://mlsanity.com/paper/2405.20445/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 53 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [A critical look at the evaluation of GNNs under heterophily: Are we really making progress?](https://mlsanity.com/paper/2302.11640/) (2023)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [GraphGPT: Graph Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2310.13023/) (2023)
- [struc2vec: Learning Node Representations from Structural Identity](https://mlsanity.com/paper/1704.03165/) (2017)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [Revisiting Heterophily For Graph Neural Networks](https://mlsanity.com/paper/2210.07606/) (2022)
- [Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning](https://mlsanity.com/paper/2010.16103/) (2020)
- [Let Your Graph Do the Talking: Encoding Structured Data for LLMs](https://mlsanity.com/paper/2402.05862/) (2024)
- [GraphText: Graph Reasoning in Text Space](https://mlsanity.com/paper/2310.01089/) (2023)
- [GraphLLM: Boosting Graph Reasoning Ability of Large Language Model](https://mlsanity.com/paper/2310.05845/) (2023)
- [Towards Foundation Models for Knowledge Graph Reasoning](https://mlsanity.com/paper/2310.04562/) (2023)
- [From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction](https://mlsanity.com/paper/2310.16802/) (2023)
- [On the Scalability of GNNs for Molecular Graphs](https://mlsanity.com/paper/2404.11568/) (2024)

## Built on by (most cited first, 30 of 39)

- [Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data](https://mlsanity.com/paper/2510.06377/) (2025)
- [The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges](https://mlsanity.com/paper/2407.09618/) (2024)
- [GraphPFN: A Prior-Data Fitted Graph Foundation Model](https://mlsanity.com/paper/2509.21489/) (2025)
- [Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models](https://mlsanity.com/paper/2506.14291/) (2025)
- [Bringing Graphs to the Table: Zero-shot Node Classification via Tabular Foundation Models](https://mlsanity.com/paper/2509.07143/) (2025)
- [Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks](https://mlsanity.com/paper/2412.12456/) (2024)
- [Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?](https://mlsanity.com/paper/2512.08798/) (2025)
- [Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors](https://mlsanity.com/paper/2604.19028/) (2026)
- [G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge](https://mlsanity.com/paper/2509.24276/) (2025)
- [Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs](https://mlsanity.com/paper/2412.17609/) (2024)
- [View Space: Learning Representation across Arbitrary Graphs](https://mlsanity.com/paper/2512.11561/) (2025)
- [Billion-Scale Graph Foundation Models](https://mlsanity.com/paper/2602.04768/) (2026)
- [GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning](https://mlsanity.com/paper/2510.04567/) (2025)
- [Node4All: Learning Node Representation Beyond Datasets](https://mlsanity.com/paper/2607.17272/) (2026)
- [Learning Representations for Reasoning: Generalizing Across Diverse Structures](https://mlsanity.com/paper/2410.13018/) (2024)
- [Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction](https://mlsanity.com/paper/2601.17469/) (2026)
- [GraphSeek: Next-Generation Graph Analytics with LLMs](https://mlsanity.com/paper/2602.11052/) (2026)
- [Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence](https://mlsanity.com/paper/2603.21601/) (2026)
- [GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning](https://mlsanity.com/paper/2605.14809/) (2026)
- [Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation](https://mlsanity.com/paper/2606.22429/) (2026)
- [LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2609.05955/) (2026)
- [Out-of-Distribution Generalization in Graph Foundation Models](https://mlsanity.com/paper/2601.21067/) (2026)
- [Learning to Approximate Uniform Facility Location via Graph Neural Networks](https://mlsanity.com/paper/2602.13155/) (2026)
- [A Cross-graph Tuning-free GNN Prompting Framework](https://mlsanity.com/paper/2604.00399/) (2026)
- [DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation](https://mlsanity.com/paper/2604.10882/) (2026)
- [Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning](https://mlsanity.com/paper/2604.22031/) (2026)
- [Mini-Batch Class Composition Bias in Link Prediction](https://mlsanity.com/paper/2604.25978/) (2026)
- [Closed-Form Node Classification with Exact Graph Unlearning](https://mlsanity.com/paper/2605.25662/) (2026)
- [Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles](https://mlsanity.com/paper/2606.03270/) (2026)
- [SPR: Toward a Graph Foundation Model for Transferable Graph Cognition via Spectral Patterns and Relational Geometry](https://mlsanity.com/paper/2606.03315/) (2026)

## Abstract (arXiv)

One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-inductive setup, where models should perform inference on arbitrary test graphs with new structures, feature and label spaces. We propose GraphAny as the first attempt at this challenging setup. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, which can be naturally applied to graphs with any feature and label spaces. To further build a stronger model with learning capacity, we fuse multiple LinearGNN predictions with learned inductive attention scores. Specifically, the attention module is carefully parameterized as a function of the entropy-normalized distance features between pairs of LinearGNN predictions to ensure generalization to new graphs. Empirically, GraphAny trained on a single Wisconsin dataset with only 120 labeled nodes can generalize to 30 new graphs with an average accuracy of 67.26%, surpassing not only all inductive baselines, but also strong transductive methods trained separately on each of the 30 test graphs.