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

arXiv: https://arxiv.org/abs/2602.08592 · HTML: https://mlsanity.com/paper/2602.08592/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 28 of 28)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [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)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [Graph Foundation Models: Concepts, Opportunities and Challenges](https://mlsanity.com/paper/2310.11829/) (2023)
- [LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence](https://mlsanity.com/paper/2509.03505/) (2025)
- [Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction](https://mlsanity.com/paper/2206.04216/) (2022)
- [Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking](https://mlsanity.com/paper/2306.10453/) (2023)
- [Neural Common Neighbor with Completion for Link Prediction](https://mlsanity.com/paper/2302.00890/) (2023)
- [TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks](https://mlsanity.com/paper/2402.11137/) (2024)
- [A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities](https://mlsanity.com/paper/2502.17361/) (2025)
- [TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems](https://mlsanity.com/paper/2502.02527/) (2025)
- [Turning Tabular Foundation Models into Graph Foundation Models](https://mlsanity.com/paper/2508.20906/) (2025)
- [Revisiting Link Prediction: A Data Perspective](https://mlsanity.com/paper/2310.00793/) (2023)
- [GraphPFN: A Prior-Data Fitted Graph Foundation Model](https://mlsanity.com/paper/2509.21489/) (2025)
- [In-Context Data Distillation with TabPFN](https://mlsanity.com/paper/2402.06971/) (2024)
- [Pure Message Passing Can Estimate Common Neighbor for Link Prediction](https://mlsanity.com/paper/2309.00976/) (2023)
- [LPFormer: An Adaptive Graph Transformer for Link Prediction](https://mlsanity.com/paper/2310.11009/) (2023)
- [Universal Link Predictor By In-Context Learning on Graphs](https://mlsanity.com/paper/2402.07738/) (2024)
- [Mixture of Link Predictors on Graphs](https://mlsanity.com/paper/2402.08583/) (2024)
- [Tabular Foundation Models are Strong Graph Anomaly Detectors](https://mlsanity.com/paper/2601.17301/) (2026)
- [A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation](https://mlsanity.com/paper/2508.04645/) (2025)
- [MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning](https://mlsanity.com/paper/2510.23013/) (2025)

## Built on by (most cited first, 7 of 7)

- [Beyond IID: How General Are Tabular Foundation Models, Really?](https://mlsanity.com/paper/2606.30410/) (2026)
- [KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning](https://mlsanity.com/paper/2605.14907/) (2026)
- [Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment](https://mlsanity.com/paper/2607.11374/) (2026)
- [LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2609.05955/) (2026)
- [Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks](https://mlsanity.com/paper/2608.08567/) (2026)
- [Training Graph Foundation Models on The Web Graph](https://mlsanity.com/paper/2609.30894/) (2026)
- [To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks](https://mlsanity.com/paper/2610.06694/) (2026)

## Abstract (arXiv)

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.