# PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning

arXiv: https://arxiv.org/abs/2609.04832 · HTML: https://mlsanity.com/paper/2609.04832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [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)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Dataless Knowledge Fusion by Merging Weights of Language Models](https://mlsanity.com/paper/2212.09849/) (2022)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Personalized Cross-Silo Federated Learning on Non-IID Data](https://mlsanity.com/paper/2007.03797/) (2020)
- [PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization](https://mlsanity.com/paper/1905.13727/) (2019)
- [Personalized Federated Learning with First Order Model Optimization](https://mlsanity.com/paper/2012.08565/) (2020)
- [Federated Graph Classification over Non-IID Graphs](https://mlsanity.com/paper/2106.13423/) (2021)
- [Federated Learning on Non-IID Graphs via Structural Knowledge Sharing](https://mlsanity.com/paper/2211.13009/) (2022)
- [FedGTA: Topology-aware Averaging for Federated Graph Learning](https://mlsanity.com/paper/2401.11755/) (2024)
- [Relaxed Contrastive Learning for Federated Learning](https://mlsanity.com/paper/2401.04928/) (2024)
- [FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation](https://mlsanity.com/paper/2310.00339/) (2023)
- [FedFisher: Leveraging Fisher Information for One-Shot Federated Learning](https://mlsanity.com/paper/2403.12329/) (2024)
- [FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs](https://mlsanity.com/paper/2208.13685/) (2022)
- [Personalized One-shot Federated Graph Learning for Heterogeneous Clients](https://mlsanity.com/paper/2411.11304/) (2024)
- [Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections](https://mlsanity.com/paper/2505.23864/) (2025)

## Abstract (arXiv)

Client heterogeneity creates both an opportunity and a risk in personalized federated graph learning. Knowledge held by other subgraphs may complement a receiver's Local model, but an incompatible transfer can override reliable predictions. One-shot communication sharpens this tension because an unsuitable server return cannot be corrected later. We introduce PACE, which treats collaborative knowledge as a compact correction to a complete Local predictor rather than as its replacement. Each client uploads a rank-r update carrier and a diagonal sketch of propagated message moments. The server uses them to construct a propagation-aware, receiver-anchored correction, while the receiver retains its full Local model. Convex negative-log-likelihood calibration (CNLL) then selects one coefficient between Local and External logits using validation nodes; model parameters remain fixed and no feedback is sent. At Rank-6, personalized returns occupy 9.6-17.6% of dense tensor bytes across the six evaluated datasets. The correction receives nonzero weight and improves both Accuracy and weighted-F1 over Local on five datasets; on ogbn-arxiv, CNLL assigns zero predictive weight to the correction and preserves Local predictions exactly. Applying the same CNLL rule to matched baselines on three citation datasets does not account for these gains. The central result is therefore that a small transported correction can augment a complete Local model when receiver evidence supports it while leaving the Local prediction unchanged otherwise.