# Curriculum Guided Personalized Subgraph Federated Learning

arXiv: https://arxiv.org/abs/2509.00402 · HTML: https://mlsanity.com/paper/2509.00402/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 30 Aug 2025.

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

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks](https://mlsanity.com/paper/1802.03796/) (2018)
- [Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning](https://mlsanity.com/paper/2210.08090/) (2022)
- [Federated Graph Neural Networks: Overview, Techniques and Challenges](https://mlsanity.com/paper/2202.07256/) (2022)
- [FedGTA: Topology-aware Averaging for Federated Graph Learning](https://mlsanity.com/paper/2401.11755/) (2024)
- [CLNode: Curriculum Learning for Node Classification](https://mlsanity.com/paper/2206.07258/) (2022)
- [On Node Features for Graph Neural Networks](https://mlsanity.com/paper/1911.08795/) (2019)
- [FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference](https://mlsanity.com/paper/2410.20105/) (2024)
- [Curriculum Graph Machine Learning: A Survey](https://mlsanity.com/paper/2302.02926/) (2023)
- [Federated Graph Learning with Structure Proxy Alignment](https://mlsanity.com/paper/2408.09393/) (2024)
- [Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First](https://mlsanity.com/paper/2310.18735/) (2023)
- [When Do Curricula Work in Federated Learning?](https://mlsanity.com/paper/2212.12712/) (2022)
- [Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective](https://mlsanity.com/paper/2402.04621/) (2024)
- [Disambiguated Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2402.08824/) (2024)
- [CIMAGE: Exploiting the Conditional Independence in Masked Graph Auto-encoders](https://mlsanity.com/paper/2503.07852/) (2025)
- [Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition](https://mlsanity.com/paper/2504.12011/) (2025)

## Built on by (most cited first, 4 of 4)

- [Federated Recommender System with Data Valuation for E-commerce Platform](https://mlsanity.com/paper/2509.11196/) (2025)
- [Collaborative Adaptive Curriculum for Progressive Knowledge Distillation](https://mlsanity.com/paper/2603.20296/) (2026)
- [Low-pass Personalized Subgraph Federated Recommendation](https://mlsanity.com/paper/2603.20338/) (2026)
- [vFedProtoQNAS: Prototype-Guided Personalized Quantum Neural Architecture Search for Virtual Federated Learning](https://mlsanity.com/paper/2610.01718/) (2026)

## Abstract (arXiv)

Subgraph Federated Learning (FL) aims to train Graph Neural Networks (GNNs) across distributed private subgraphs, but it suffers from severe data heterogeneity. To mitigate data heterogeneity, weighted model aggregation personalizes each local GNN by assigning larger weights to parameters from clients with similar subgraph characteristics inferred from their current model states. However, the sparse and biased subgraphs often trigger rapid overfitting, causing the estimated client similarity matrix to stagnate or even collapse. As a result, aggregation loses effectiveness as clients reinforce their own biases instead of exploiting diverse knowledge otherwise available. To this end, we propose a novel personalized subgraph FL framework called Curriculum guided personalized sUbgraph Federated Learning (CUFL). On the client side, CUFL adopts Curriculum Learning (CL) that adaptively selects edges for training according to their reconstruction scores, exposing each GNN first to easier, generic cross-client substructures and only later to harder, client-specific ones. This paced exposure prevents early overfitting to biased patterns and enables gradual personalization. By regulating personalization, the curriculum also reshapes server aggregation from exchanging generic knowledge to propagating client-specific knowledge. Further, CUFL improves weighted aggregation by estimating client similarity using fine-grained structural indicators reconstructed on a random reference graph. Extensive experiments on six benchmark datasets confirm that CUFL achieves superior performance compared to relevant baselines. Code is available at https://github.com/Kang-Min-Ku/CUFL.git.