# FOS: A Large-Scale Temporal Graph Benchmark for Scientific Interdisciplinary Link Prediction

arXiv: https://arxiv.org/abs/2511.18631 · HTML: https://mlsanity.com/paper/2511.18631/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Builds on (most cited first, 20 of 20)

- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Growth rates of modern science: A latent piecewise growth curve approach to model publication numbers from established and new literature databases](https://mlsanity.com/paper/2012.07675/) (2020)
- [Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references](https://mlsanity.com/paper/1402.4578/) (2014)
- [Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network](https://mlsanity.com/paper/2210.00881/) (2022)
- [TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs](https://mlsanity.com/paper/2406.09639/) (2024)
- [Predicting Research Trends with Semantic and Neural Networks with an application in Quantum Physics](https://mlsanity.com/paper/1906.06843/) (2019)
- [Laplacian Change Point Detection for Dynamic Graphs](https://mlsanity.com/paper/2007.01229/) (2020)
- [Forecasting high-impact research topics via machine learning on evolving knowledge graphs](https://mlsanity.com/paper/2402.08640/) (2024)
- [Topic Space Trajectories: A case study on machine learning literature](https://mlsanity.com/paper/2010.12294/) (2020)
- [Whats next? Forecasting scientific research trends](https://mlsanity.com/paper/2305.04133/) (2023)
- [Computing Maximum Matchings in Temporal Graphs](https://mlsanity.com/paper/1905.05304/) (2019)
- [Comparing Temporal Graphs Using Dynamic Time Warping](https://mlsanity.com/paper/1810.06240/) (2018)
- [The Boundary-Spanning Mechanisms of Nobel Prize Winning Papers](https://mlsanity.com/paper/2102.04616/) (2021)

## Built on by (most cited first, 2 of 2)

- [SciImpact: A Multi-Dimensional, Multi-Field Benchmark for Scientific Impact Prediction](https://mlsanity.com/paper/2604.17141/) (2026)
- [SCPP: A Unified Python Library for Soft Clustering](https://mlsanity.com/paper/2607.19620/) (2026)

## Abstract (arXiv)

Interdisciplinary scientific breakthroughs mostly emerge unexpectedly, and forecasting the formation of novel research fields remains a major challenge. We introduce FOS (Future Of Science), a comprehensive time-aware graph-based benchmark that reconstructs annual co-occurrence graphs of 65,027 research sub-fields (spanning 19 general domains) over the period 1827-2024. In these graphs, edges denote the co-occurrence of two fields in a single publication and are timestamped with the corresponding publication year. Nodes are enriched with semantic embeddings, and edges are characterized by temporal and topological descriptors. We formulate the prediction of new field-pair linkages as a temporal link-prediction task, emphasizing the "first-time" connections that signify pioneering interdisciplinary directions. Through extensive experiments, we evaluate a suite of state-of-the-art temporal graph architectures under multiple negative-sampling regimes and show that (i) embedding long-form textual descriptions of fields significantly boosts prediction accuracy, and (ii) distinct model classes excel under different evaluation settings. Case analyses show that top-ranked link predictions on FOS align with field pairings that emerge in subsequent years of academic publications. We publicly release FOS, along with its temporal data splits and evaluation code, to establish a reproducible benchmark for advancing research in predicting scientific frontiers.