# Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification

arXiv: https://arxiv.org/abs/2610.17582 · HTML: https://mlsanity.com/paper/2610.17582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 13 Oct 2026.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media](https://mlsanity.com/paper/1809.01286/) (2018)
- [Structured Sequence Modeling with Graph Convolutional Recurrent Networks](https://mlsanity.com/paper/1612.07659/) (2016)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data](https://mlsanity.com/paper/2108.01099/) (2021)
- [User Preference-aware Fake News Detection](https://mlsanity.com/paper/2104.12259/) (2021)
- [Generalizing Graph Neural Networks on Out-Of-Distribution Graphs](https://mlsanity.com/paper/2111.10657/) (2021)
- [TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs](https://mlsanity.com/paper/2203.14883/) (2022)
- [Graph Out-of-Distribution Generalization via Causal Intervention](https://mlsanity.com/paper/2402.11494/) (2024)
- [A survey of dynamic graph neural networks](https://mlsanity.com/paper/2404.18211/) (2024)
- [GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs](https://mlsanity.com/paper/2110.05598/) (2021)
- [DECOR: Degree-Corrected Social Graph Refinement for Fake News Detection](https://mlsanity.com/paper/2307.00077/) (2023)
- [SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning](https://mlsanity.com/paper/2404.07941/) (2024)
- [Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs](https://mlsanity.com/paper/2402.11153/) (2024)
- [Dynamic Graph Node Classification via Time Augmentation](https://mlsanity.com/paper/2212.03449/) (2022)
- [Efficient and Effective Implicit Dynamic Graph Neural Network](https://mlsanity.com/paper/2406.17894/) (2024)
- [Hypergraph-Based Dynamic Graph Node Classification](https://mlsanity.com/paper/2412.20321/) (2024)

## Abstract (arXiv)

Entities in real-world systems often evolve over time: users shift between information consumption patterns, researchers migrate between fields, and firms transition between financial risk states. When such systems are modeled as dynamic graphs, these transitions correspond to nodes whose class labels change between consecutive snapshots, which we call shifters. Correctly classifying shifters is often more consequential than classifying stable nodes with persistent labels, as detecting such transitions enables timely intervention in high-stakes settings. Yet, we identify a systematic failure mode across all major dynamic graph neural network architectures: shifter performance consistently lags behind stable nodes, with errors concentrated on the old label. Our structural analysis traces this failure to embedding inertia: neighborhood aggregation keeps shifter representations anchored to the old-class centroid, and this effect is strongest precisely where it is hardest to correct, namely for shifters whose neighborhoods remain aligned with the old class. Guided by this finding, we propose CHASE, a model-agnostic CHange-Aware framework for Shifting nodEs that wraps any dynamic GNN with targeted components for detecting label shifts and overriding stale neighborhood signals. CHASE consistently improves shifter performance across all tested models and datasets (up to 114.9% and 202.5% improvement on accuracy and F1 score, respectively) while preserving stable-node performance. We additionally contribute three dynamic graph benchmarks with naturally shifting labels, filling a gap in existing resources. The source code is available at https://github.com/jhkim611/CHASE