HybridFL: A Federated Learning Approach for Financial Crime Detection

TL;DR

HybridFL tackles hybrid data partitions across financial institutions by fusing horizontal and vertical information without sharing raw data. It introduces a four-model architecture with a transaction encoder, sender/receiver encoders, and a fusion head, trained through gradient exchange and periodic FedAvg synchronization to learn a joint predictor under locality constraints. The learning objective is $\min_{\Theta} \mathbb{E}_{(x,y) \sim \mathcal{D}} \mathcal{L}(f(x; \Theta), y)$, balancing information from transaction-level and account-level features. Experiments on AMLSim and SWIFT show HybridFL significantly outperforms a transaction-only baseline and approaches centralized performance, demonstrating practical privacy-preserving collaboration for financial crime detection; future work will incorporate differential privacy or secure aggregation to further mitigate privacy risks while assessing accuracy trade-offs.

Abstract

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables multiple parties to collaboratively train models on privately owned data without sharing raw information. While standard FL typically addresses either horizontal or vertical data partitions, many real-world scenarios exhibit a complex hybrid distribution. This paper proposes Hybrid Federated Learning (HybridFL) to address data split both horizontally across disjoint users and vertically across complementary feature sets. We evaluate HybridFL in a financial crime detection context, where a transaction party holds transaction-level attributes and multiple banks maintain private account-level features. By integrating horizontal aggregation and vertical feature fusion, the proposed architecture enables joint learning while strictly preserving data locality. Experiments on AMLSim and SWIFT datasets demonstrate that HybridFL significantly outperforms the transaction-only local model and achieves performance comparable to a centralized benchmark.

Figures (2)

• Figure 1: Illustration of the hybrid data partition. The transaction party holds transaction-level records, while Banks A and B each maintain private account-level data for their respective customers. Transactions link the sender and receiver accounts, creating vertical connections across institutions and horizontal separation within each bank.
• Figure 2: HybridFL training workflow: The transaction party acts as the active party, fusing embeddings received from the sender and receiver banks (passive parties) with its own transaction embedding to produce a prediction and compute the loss and gradients with respect to embeddings. Computed gradients are sent back to the corresponding banks for updating local sender and receiver models. Bank local models are periodically synchronized via Federated Averaging