TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models

2026-02-09

AI Summary

Existing graph foundation models for link prediction are limited by the scale of pretraining or their reliance on textual attributes, hindering generalization across datasets and domains. This work proposes a novel, tuning-free approach by introducing Tabular Foundation Models (TFMs) to link prediction. Leveraging the in-context learning capability of TFMs, the method generates synthetic data via a structural causal model and constructs enriched local–global contextual representations through prototype-augmented mechanisms, coupled with a topology-aware link encoder. Evaluated on six cross-domain graph benchmarks, the approach significantly outperforms state-of-the-art models, achieving a breakthrough in general-purpose link prediction without requiring textual features or dataset-specific fine-tuning.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: (Large) Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Link prediction is a fundamental task in graph machine learning with widespread applications such as recommendation systems, drug discovery, knowledge graphs, etc. In the foundation model era, how to develop universal link prediction methods across datasets and domains becomes a key problem, with some initial attempts adopting Graph Foundation Models utilizing Graph Neural Networks and Large Language Models. However, the existing methods face notable limitations, including limited pre-training scale or heavy reliance on textual information. Motivated by the success of tabular foundation models (TFMs) in achieving universal prediction across diverse tabular datasets, we explore an alternative approach by TFMs, which are pre-trained on diverse synthetic datasets sampled from structural causal models and support strong in-context learning independent of textual attributes. Nevertheless, adapting TFMs for link prediction faces severe technical challenges such as how to obtain the necessary context and capture link-centric topological information. To solve these challenges, we propose TFMLinker (Tabular Foundation Model for Link Predictor), aiming to leverage the in-context learning capabilities of TFMs to perform link prediction across diverse graphs without requiring dataset-specific fine-tuning. Specifically, we first develop a prototype-augmented local-global context module to construct context that captures both graph-specific and cross-graph transferable patterns. Next, we design a universal topology-aware link encoder to capture link-centric topological information and generate link representations as inputs for the TFM. Finally, we employ the TFM to predict link existence through in-context learning. Experiments on 6 graph benchmarks across diverse domains demonstrate the superiority of our method over state-of-the-art baselines without requiring dataset-specific finetuning.

Problem

• link prediction
• universal prediction
• graph machine learning
• foundation models
• in-context learning

Innovation

• Tabular Foundation Models
• In-Context Learning
• Link Prediction
• Topology-Aware Encoding
• Universal Graph Learning