# FTM: A Frame-level Timeline Modeling Method for Temporal Graph Representation Learning

## TL;DR

The paper introduces FTM, a novel method for temporal graph representation learning that effectively captures both short-term and long-term features, improving robustness and domain generality of graph neural networks.

## Contribution

FTM is a new frame-level timeline modeling approach that enhances temporal graph learning by preserving short-term features and modeling long-term dynamics, compatible with existing GNNs.

## Key findings

- Significant performance improvements on benchmark datasets.
- Enhanced robustness and domain generality of temporal graph models.
- Effective capture of both short-term and long-term features.

## Abstract

Learning representations for graph-structured data is essential for graph analytical tasks. While remarkable progress has been made on static graphs, researches on temporal graphs are still in its beginning stage. The bottleneck of the temporal graph representation learning approach is the neighborhood aggregation strategy, based on which graph attributes share and gather information explicitly. Existing neighborhood aggregation strategies fail to capture either the short-term features or the long-term features of temporal graph attributes, leading to unsatisfactory model performance and even poor robustness and domain generality of the representation learning method. To address this problem, we propose a Frame-level Timeline Modeling (FTM) method that helps to capture both short-term and long-term features and thus learns more informative representations on temporal graphs. In particular, we present a novel link-based framing technique to preserve the short-term features and then incorporate a timeline aggregator module to capture the intrinsic dynamics of graph evolution as long-term features. Our method can be easily assembled with most temporal GNNs. Extensive experiments on common datasets show that our method brings great improvements to the capability, robustness, and domain generality of backbone methods in downstream tasks. Our code can be found at https://github.com/yeeeqichen/FTM.