# Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs

arXiv: https://arxiv.org/abs/2306.01240 · HTML: https://mlsanity.com/paper/2306.01240/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 55 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 30 of 38)

- [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)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [Learning Discrete Structures for Graph Neural Networks](https://mlsanity.com/paper/1903.11960/) (2019)
- [Gradient-Based Neural DAG Learning](https://mlsanity.com/paper/1906.02226/) (2019)
- [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://mlsanity.com/paper/1711.10677/) (2017)
- [SecureBoost: A Lossless Federated Learning Framework](https://mlsanity.com/paper/1901.08755/) (2019)
- [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018)
- [Discrete Graph Structure Learning for Forecasting Multiple Time Series](https://mlsanity.com/paper/2101.06861/) (2021)
- [Federated Learning from Pre-Trained Models: A Contrastive Learning Approach](https://mlsanity.com/paper/2209.10083/) (2022)
- [SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks](https://mlsanity.com/paper/2102.05034/) (2021)
- [Label Leakage and Protection in Two-party Split Learning](https://mlsanity.com/paper/2102.08504/) (2021)
- [VAFL: a Method of Vertical Asynchronous Federated Learning](https://mlsanity.com/paper/2007.06081/) (2020)

## Built on by (most cited first, 8 of 8)

- [Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data](https://mlsanity.com/paper/2502.19752/) (2025)
- [Graph Concept Bottleneck Models](https://mlsanity.com/paper/2508.14255/) (2025)
- [Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data](https://mlsanity.com/paper/2510.22880/) (2025)
- [Federated Granger Causality Learning for Interdependent Clients with State Space Representation](https://mlsanity.com/paper/2501.13890/) (2025)
- [Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data](https://mlsanity.com/paper/2602.07081/) (2026)
- [Expressive and Scalable Quantum Fusion for Multimodal Learning](https://mlsanity.com/paper/2510.06938/) (2025)
- [Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability](https://mlsanity.com/paper/2602.13485/) (2026)
- [Learning Unknown Interdependencies for Decentralized Root Cause Analysis in Nonlinear Dynamical Systems](https://mlsanity.com/paper/2602.21928/) (2026)

## Abstract (arXiv)

Learning an effective global model on private and decentralized datasets has become an increasingly important challenge of machine learning when applied in practice. Existing distributed learning paradigms, such as Federated Learning, enable this via model aggregation which enforces a strong form of modeling homogeneity and synchronicity across clients. This is however not suitable to many practical scenarios. For example, in distributed sensing, heterogeneous sensors reading data from different views of the same phenomenon would need to use different models for different data modalities. Local learning therefore happens in isolation but inference requires merging the local models to achieve consensus. To enable consensus among local models, we propose a feature fusion approach that extracts local representations from local models and incorporates them into a global representation that improves the prediction performance. Achieving this requires addressing two non-trivial problems. First, we need to learn an alignment between similar feature components which are arbitrarily arranged across clients to enable representation aggregation. Second, we need to learn a consensus graph that captures the high-order interactions between local feature spaces and how to combine them to achieve a better prediction. This paper presents solutions to these problems and demonstrates them in real-world applications on time series data such as power grids and traffic networks.