# Semi-supervised Graph Embedding Approach to Dynamic Link Prediction

arXiv: https://arxiv.org/abs/1610.04351 · HTML: https://mlsanity.com/paper/1610.04351/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2016.

## Built on by (most cited first, 9 of 9)

- [A Survey on Embedding Dynamic Graphs](https://mlsanity.com/paper/2101.01229/) (2021)
- [GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs](https://mlsanity.com/paper/2110.05598/) (2021)
- [Time-Aware Neighbor Sampling for Temporal Graph Networks](https://mlsanity.com/paper/2112.09845/) (2021)
- [Weakly Supervised Learning for Analyzing Political Campaigns on Facebook](https://mlsanity.com/paper/2210.10669/) (2022)
- [Temporal Graph Network Embedding with Causal Anonymous Walks Representations](https://mlsanity.com/paper/2108.08754/) (2021)
- [Predicting Corporate Risk by Jointly Modeling Company Networks and Dialogues in Earnings Conference Calls](https://mlsanity.com/paper/2206.06174/) (2022)
- [Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism](https://mlsanity.com/paper/2106.01678/) (2021)
- [Who Should I Engage with At What Time? A Missing Event Aware Temporal Graph Neural Network](https://mlsanity.com/paper/2301.08399/) (2023)
- [Graph Enhanced Trajectory Anomaly Detection](https://mlsanity.com/paper/2509.18386/) (2025)

## Abstract (arXiv)

We propose a simple discrete time semi-supervised graph embedding approach to link prediction in dynamic networks. The learned embedding reflects information from both the temporal and cross-sectional network structures, which is performed by defining the loss function as a weighted sum of the supervised loss from past dynamics and the unsupervised loss of predicting the neighborhood context in the current network. Our model is also capable of learning different embeddings for both formation and dissolution dynamics. These key aspects contributes to the predictive performance of our model and we provide experiments with three real--world dynamic networks showing that our method is comparable to state of the art methods in link formation prediction and outperforms state of the art baseline methods in link dissolution prediction.