Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach
Quick Answer
The FedEPD framework enhances Federated Graph Learning by addressing long-tailed data distributions, achieving up to 4.97% accuracy and 5.48% Macro-F1 improvements.
Quick Take
It employs dual decoupling for topological purification and semantic recalibration, effectively protecting minority nodes from structural noise.
Key Points
- FedEPD addresses long-tailed distributions in Federated Graph Learning.
- Utilizes Dirichlet energy pruning for filtering heterophilic edges.
- Implements a two-stage optimization to protect majority decision boundaries.
- Achieves state-of-the-art performance on long-tailed benchmarks.
- Demonstrates significant improvements in accuracy and Macro-F1 scores.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Federated Graph Learning facilitates collaborative graph modeling across distributed clients while preserving data privacy. However, real-world data categories frequently exhibit long-tailed distributions. Such statistical scarcity severely degrades performance in two ways: it biases the global model toward majority classes, and it structurally isolates minority nodes by submerging them in heterophilic, head-dominated neighborhoods. While existing methods attempt topology-agnostic statistical compensations, they often fail under data scarcity. Instead of recovering tail nodes, they overfit the structural noise from adjacent dominant classes, leading to representation degradation. To address these limitations, we propose FedEPD, a framework built on a dual decoupling paradigm that separates topological purification from semantic recalibration. Specifically, FedEPD utilizes distribution-aware Dirichlet energy pruning to filter spatial heterophilic edges. It then overcomes Non-IID distribution shifts by extracting robust global prototypes from topologically central nodes, which are incorporated into local representations via a spatial low-pass prototype injection. Furthermore, a two stage alternating optimization strategy strictly protects majority decision boundaries while improving minority accuracy. Extensive experiments demonstrate that FedEPD achieves state-of-the-art performance across diverse long-tailed benchmarks, yielding absolute improvements of up to 4.97% in Accuracy and 5.48% in Macro-F1.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.24237 [cs.AI] |
| (or arXiv:2606.24237v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.24237 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xunkai Li [view email]
[v1]
Tue, 23 Jun 2026 07:25:40 UTC (543 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.