# Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modeling

arXiv: https://arxiv.org/abs/2406.11891 · HTML: https://mlsanity.com/paper/2406.11891/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [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)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [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)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Not too little, not too much: a theoretical analysis of graph (over)smoothing](https://mlsanity.com/paper/2205.12156/) (2022)
- [GeniePath: Graph Neural Networks with Adaptive Receptive Paths](https://mlsanity.com/paper/1802.00910/) (2018)
- [Provably expressive temporal graph networks](https://mlsanity.com/paper/2209.15059/) (2022)
- [Policy-GNN: Aggregation Optimization for Graph Neural Networks](https://mlsanity.com/paper/2006.15097/) (2020)
- [Search to aggregate neighborhood for graph neural network](https://mlsanity.com/paper/2104.06608/) (2021)
- [Pooling Architecture Search for Graph Classification](https://mlsanity.com/paper/2108.10587/) (2021)
- [Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection](https://mlsanity.com/paper/2212.12488/) (2022)
- [Robustifying Token Attention for Vision Transformers](https://mlsanity.com/paper/2303.11126/) (2023)
- [AutoGEL: An Automated Graph Neural Network with Explicit Link Information](https://mlsanity.com/paper/2112.01064/) (2021)
- [TIGER: Temporal Interaction Graph Embedding with Restarts](https://mlsanity.com/paper/2302.06057/) (2023)
- [RDGSL: Dynamic Graph Representation Learning with Structure Learning](https://mlsanity.com/paper/2309.02025/) (2023)
- [Prompt Learning on Temporal Interaction Graphs](https://mlsanity.com/paper/2402.06326/) (2024)
- [SPEED: Streaming Partition and Parallel Acceleration for Temporal Interaction Graph Embedding](https://mlsanity.com/paper/2308.14129/) (2023)
- [iLoRE: Dynamic Graph Representation with Instant Long-term Modeling and Re-occurrence Preservation](https://mlsanity.com/paper/2309.02012/) (2023)
- [The Geometry of Information Cocoon: Analyzing the Cultural Space with Word Embedding Models](https://mlsanity.com/paper/2007.10083/) (2020)

## Built on by (most cited first, 8 of 8)

- [Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models](https://mlsanity.com/paper/2503.14411/) (2025)
- [A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2505.04461/) (2025)
- [DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning](https://mlsanity.com/paper/2407.18523/) (2024)
- [Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs](https://mlsanity.com/paper/2502.19651/) (2025)
- [Graph Retention Networks for Dynamic Graphs](https://mlsanity.com/paper/2411.11259/) (2024)
- [Rethinking Time Encoding via Learnable Transformation Functions](https://mlsanity.com/paper/2505.00887/) (2025)
- [Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models](https://mlsanity.com/paper/2605.13540/) (2026)
- [GRAVITY: A Controversial Graph Representation Learning for Vertex Classification](https://mlsanity.com/paper/2508.08954/) (2025)

## Abstract (arXiv)

Temporal Graph Networks (TGNs) have demonstrated their remarkable performance in modeling temporal interaction graphs. These works can generate temporal node representations by encoding the surrounding neighborhoods for the target node. However, an inherent limitation of existing TGNs is their reliance on fixed, hand-crafted rules for neighborhood encoding, overlooking the necessity for an adaptive and learnable neighborhood that can accommodate both personalization and temporal evolution across different timestamps. In this paper, we aim to enhance existing TGNs by introducing an adaptive neighborhood encoding mechanism. We present SEAN, a flexible plug-and-play model that can be seamlessly integrated with existing TGNs, effectively boosting their performance. To achieve this, we decompose the adaptive neighborhood encoding process into two phases: (i) representative neighbor selection, and (ii) temporal-aware neighborhood information aggregation. Specifically, we propose the Representative Neighbor Selector component, which automatically pinpoints the most important neighbors for the target node. It offers a tailored understanding of each node's unique surrounding context, facilitating personalization. Subsequently, we propose a Temporal-aware Aggregator, which synthesizes neighborhood aggregation by selectively determining the utilization of aggregation routes and decaying the outdated information, allowing our model to adaptively leverage both the contextually significant and current information during aggregation. We conduct extensive experiments by integrating SEAN into three representative TGNs, evaluating their performance on four public datasets and one financial benchmark dataset introduced in this paper. The results demonstrate that SEAN consistently leads to performance improvements across all models, achieving SOTA performance and exceptional robustness.