# Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions

arXiv: https://arxiv.org/abs/1909.10367 · HTML: https://mlsanity.com/paper/1909.10367/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2019.

## Built on by (most cited first, 11 of 11)

- [A Survey on Embedding Dynamic Graphs](https://mlsanity.com/paper/2101.01229/) (2021)
- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [A survey of dynamic graph neural networks](https://mlsanity.com/paper/2404.18211/) (2024)
- [TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics](https://mlsanity.com/paper/2502.02975/) (2025)
- [NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams](https://mlsanity.com/paper/2312.02473/) (2023)
- [Future Link Prediction Without Memory or Aggregation](https://mlsanity.com/paper/2505.19408/) (2025)
- [Temporal Graph Network Embedding with Causal Anonymous Walks Representations](https://mlsanity.com/paper/2108.08754/) (2021)
- [Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU](https://mlsanity.com/paper/2210.03900/) (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)
- [Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference](https://mlsanity.com/paper/2309.02868/) (2023)

## Abstract (arXiv)

Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, long term edges are often specified by humans. Human-specified edges can be both expensive to produce and suboptimal for the downstream task. To alleviate these issues, we propose a model based on temporal point processes and variational autoencoders that learns to infer temporal attention between nodes by observing node communication. As temporal attention drives between-node feature propagation, using the dynamics of node interactions to learn this key component provides more flexibility while simultaneously avoiding issues associated with human-specified edges. We also propose a bilinear transformation layer for pairs of node features instead of concatenation, typically used in prior work, and demonstrate its superior performance in all cases. In experiments on two datasets in the dynamic link prediction task, our model often outperforms the baseline model that requires a human-specified graph. Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs.