# Universal Link Predictor By In-Context Learning on Graphs

arXiv: https://arxiv.org/abs/2402.07738 · HTML: https://mlsanity.com/paper/2402.07738/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 70 references that are in the map.
- First posted on arXiv 12 Feb 2024.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [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)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [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)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [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)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Inductive Relation Prediction by Subgraph Reasoning](https://mlsanity.com/paper/1911.06962/) (2019)
- [Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning](https://mlsanity.com/paper/2305.14160/) (2023)
- [Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers](https://mlsanity.com/paper/2212.10559/) (2022)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning](https://mlsanity.com/paper/2010.16103/) (2020)
- [Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries](https://mlsanity.com/paper/2206.11140/) (2022)
- [PRODIGY: Enabling In-context Learning Over Graphs](https://mlsanity.com/paper/2305.12600/) (2023)
- [Decoupling the Depth and Scope of Graph Neural Networks](https://mlsanity.com/paper/2201.07858/) (2022)
- [Graph Neural Networks for Link Prediction with Subgraph Sketching](https://mlsanity.com/paper/2209.15486/) (2022)
- [AFEC: Active Forgetting of Negative Transfer in Continual Learning](https://mlsanity.com/paper/2110.12187/) (2021)

## Built on by (most cited first, 13 of 13)

- [ARC: A Generalist Graph Anomaly Detector with In-Context Learning](https://mlsanity.com/paper/2405.16771/) (2024)
- [Fully-inductive Node Classification on Arbitrary Graphs](https://mlsanity.com/paper/2405.20445/) (2024)
- [From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection](https://mlsanity.com/paper/2602.18793/) (2026)
- [TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2602.08592/) (2026)
- [A Fair Evaluation of Graph Foundation Models for Node Property Prediction](https://mlsanity.com/paper/2606.24509/) (2026)
- [GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning](https://mlsanity.com/paper/2510.04567/) (2025)
- [Designing a reliable lateral movement detector using a graph foundation model](https://mlsanity.com/paper/2504.13527/) (2025)
- [Relation-Aware Graph Foundation Model](https://mlsanity.com/paper/2505.12027/) (2025)
- [Generalist Graph Anomaly Detection via Prototype-Based Distillation](https://mlsanity.com/paper/2605.26857/) (2026)
- [SASA: Semantic-Aware Contrastive Learning Framework with Separated Attention for Triple Classification](https://mlsanity.com/paper/2601.13035/) (2026)
- [Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning](https://mlsanity.com/paper/2604.22031/) (2026)
- [Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks](https://mlsanity.com/paper/2608.08567/) (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 crucial task in graph machine learning, where the goal is to infer missing or future links within a graph. Traditional approaches leverage heuristic methods based on widely observed connectivity patterns, offering broad applicability and generalizability without the need for model training. Despite their utility, these methods are limited by their reliance on human-derived heuristics and lack the adaptability of data-driven approaches. Conversely, parametric link predictors excel in automatically learning the connectivity patterns from data and achieving state-of-the-art but fail short to directly transfer across different graphs. Instead, it requires the cost of extensive training and hyperparameter optimization to adapt to the target graph. In this work, we introduce the Universal Link Predictor (UniLP), a novel model that combines the generalizability of heuristic approaches with the pattern learning capabilities of parametric models. UniLP is designed to autonomously identify connectivity patterns across diverse graphs, ready for immediate application to any unseen graph dataset without targeted training. We address the challenge of conflicting connectivity patterns-arising from the unique distributions of different graphs-through the implementation of In-context Learning (ICL). This approach allows UniLP to dynamically adjust to various target graphs based on contextual demonstrations, thereby avoiding negative transfer. Through rigorous experimentation, we demonstrate UniLP's effectiveness in adapting to new, unseen graphs at test time, showcasing its ability to perform comparably or even outperform parametric models that have been finetuned for specific datasets. Our findings highlight UniLP's potential to set a new standard in link prediction, combining the strengths of heuristic and parametric methods in a single, versatile framework.