# TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

arXiv: https://arxiv.org/abs/2206.12917 · HTML: https://mlsanity.com/paper/2206.12917/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 26 Jun 2022.

## Builds on (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods](https://mlsanity.com/paper/2110.14446/) (2021)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Graph Neural Networks with Heterophily](https://mlsanity.com/paper/2009.13566/) (2020)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot](https://mlsanity.com/paper/2108.02385/) (2021)
- [RSG: A Simple but Effective Module for Learning Imbalanced Datasets](https://mlsanity.com/paper/2106.09859/) (2021)
- [Topology-Imbalance Learning for Semi-Supervised Node Classification](https://mlsanity.com/paper/2110.04099/) (2021)
- [Adaptive Class Suppression Loss for Long-Tail Object Detection](https://mlsanity.com/paper/2104.00885/) (2021)
- [Posterior Re-calibration for Imbalanced Datasets](https://mlsanity.com/paper/2010.11820/) (2020)
- [ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networks](https://mlsanity.com/paper/2106.02817/) (2021)

## Built on by (most cited first, 30 of 41)

- [A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges](https://mlsanity.com/paper/2403.04468/) (2024)
- [Class-Imbalanced Graph Learning without Class Rebalancing](https://mlsanity.com/paper/2308.14181/) (2023)
- [Class-Imbalanced Learning on Graphs: A Survey](https://mlsanity.com/paper/2304.04300/) (2023)
- [Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification](https://mlsanity.com/paper/2304.05059/) (2023)
- [Partitioning Message Passing for Graph Fraud Detection](https://mlsanity.com/paper/2412.00020/) (2024)
- [GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2306.09612/) (2023)
- [A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions](https://mlsanity.com/paper/2308.13821/) (2023)
- [Federated Graph Learning with Structure Proxy Alignment](https://mlsanity.com/paper/2408.09393/) (2024)
- [Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition](https://mlsanity.com/paper/2310.18765/) (2023)
- [Rethinking Fair Graph Neural Networks from Re-balancing](https://mlsanity.com/paper/2407.11624/) (2024)
- [Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks](https://mlsanity.com/paper/2302.14061/) (2023)
- [LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework](https://mlsanity.com/paper/2405.13902/) (2024)
- [Over-Sampling Strategy in Feature Space for Graphs based Class-imbalanced Bot Detection](https://mlsanity.com/paper/2302.06900/) (2023)
- [RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classification](https://mlsanity.com/paper/2308.02335/) (2023)
- [DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization](https://mlsanity.com/paper/2408.04400/) (2024)
- [Mitigating Label Noise on Graph via Topological Sample Selection](https://mlsanity.com/paper/2403.01942/) (2024)
- [Cluster-guided Contrastive Class-imbalanced Graph Classification](https://mlsanity.com/paper/2412.12984/) (2024)
- [Edge Classification on Graphs: New Directions in Topological Imbalance](https://mlsanity.com/paper/2406.11685/) (2024)
- [IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2502.06280/) (2025)
- [Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph](https://mlsanity.com/paper/2406.01066/) (2024)
- [ECGN: A Cluster-Aware Approach to Graph Neural Networks for Imbalanced Classification](https://mlsanity.com/paper/2410.11765/) (2024)
- [Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning](https://mlsanity.com/paper/2507.06469/) (2025)
- [Re-understanding Graph Unlearning through Memorization](https://mlsanity.com/paper/2601.14694/) (2026)
- [EAGLE: Edge-Aware Graph Learning for Proactive Delivery Delay Prediction in Smart Logistics Networks](https://mlsanity.com/paper/2604.05254/) (2026)
- [Using Active Learning Methods to Strategically Select Essays for Automated Scoring](https://mlsanity.com/paper/2301.00628/) (2023)
- [Heterophily-Based Graph Neural Network for Imbalanced Classification](https://mlsanity.com/paper/2310.08725/) (2023)
- [Class-Balanced and Reinforced Active Learning on Graphs](https://mlsanity.com/paper/2402.10074/) (2024)
- [Automated Loss function Search for Class-imbalanced Node Classification](https://mlsanity.com/paper/2405.14133/) (2024)
- [SiMilarity-Enhanced Homophily for Multi-View Heterophilous Graph Clustering](https://mlsanity.com/paper/2410.03596/) (2024)
- [NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration](https://mlsanity.com/paper/2505.15180/) (2025)

## Abstract (arXiv)

Learning unbiased node representations under class-imbalanced graph data is challenging due to interactions between adjacent nodes. Existing studies have in common that they compensate the minor class nodes `as a group' according to their overall quantity (ignoring node connections in graph), which inevitably increase the false positive cases for major nodes. We hypothesize that the increase in these false positive cases is highly affected by the label distribution around each node and confirm it experimentally. In addition, in order to handle this issue, we propose Topology-Aware Margin (TAM) to reflect local topology on the learning objective. Our method compares the connectivity pattern of each node with the class-averaged counter-part and adaptively adjusts the margin accordingly based on that. Our method consistently exhibits superiority over the baselines on various node classification benchmark datasets with representative GNN architectures.