# STAMP: Symmetric Temporal Averaging Message Passing for Domain Adaptation in Chronologically Split Graphs

arXiv: https://arxiv.org/abs/2411.10957 · HTML: https://mlsanity.com/paper/2411.10957/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 17 Nov 2024.

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [SIGN: Scalable Inception Graph Neural Networks](https://mlsanity.com/paper/2004.11198/) (2020)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Training Graph Neural Networks with 1000 Layers](https://mlsanity.com/paper/2106.07476/) (2021)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [Contextual Stochastic Block Models](https://mlsanity.com/paper/1807.09596/) (2018)
- [Theoretical Analysis of Domain Adaptation with Optimal Transport](https://mlsanity.com/paper/1610.04420/) (2016)
- [Graph Attention Multi-Layer Perceptron](https://mlsanity.com/paper/2206.04355/) (2022)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching](https://mlsanity.com/paper/2204.11700/) (2022)
- [A New PAC-Bayesian Perspective on Domain Adaptation](https://mlsanity.com/paper/1506.04573/) (2015)
- [Efficient Heterogeneous Graph Learning via Random Projection](https://mlsanity.com/paper/2310.14481/) (2023)
- [Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2402.18875/) (2024)
- [Heterogeneous Graph Neural Networks with Loss-decrease-aware Curriculum Learning](https://mlsanity.com/paper/2405.06522/) (2024)

## Abstract (arXiv)

This paper addresses domain adaptation in graph-structured data under chronological splits. We consider transductive semi-supervised node classification (SSNC), in which labels of historical nodes are used to predict labels of more recent nodes. Temporal dependencies in graph connectivity induce distribution shifts across time, often degrading the performance of models trained on past nodes. Despite its practical relevance, domain adaptation under chronological graph splits remains relatively underexplored. We propose Symmetric Temporal Averaging Message Passing (STAMP), a timestamp-balanced operator that replaces standard neighborhood aggregation with temporally aligned propagation. We call its specialized variant for the heterogeneous ogbn-mag dataset STAMP-mag, reserving STAMP for the general formulation. By balancing messages across timestamps, STAMP enforces first-moment invariance across temporal domains while remaining scalable and easy to implement. Unlike many existing domain adaptation methods, whose assumptions are difficult to verify on graphs, STAMP relies on transparent, practically checkable conditions and is supported by theoretical analysis. Empirically, STAMP and STAMP-mag improve accuracy across all evaluated temporal graph benchmarks. STAMP achieves state-of-the-art performance on ogbn-arxiv, while STAMP-mag does so on ogbn-mag. For temporal-split Pokec, where no established benchmark exists, applying STAMP to the state-of-the-art model for the original dataset consistently improves performance under our chronological split. These results demonstrate that timestamp-balanced propagation is an effective and practical approach to mitigating temporal distribution shift in graph learning.