Abstract
Federated Learning (FL) presents a decentralized approach to model training in the agri-food sector and offers the potential for improved machine learning performance, while ensuring the safety and privacy of individual farms or data silos. However, the conventional FL approach has two major limitations. First, the heterogeneous data on individual silos can cause the global model to perform well for some clients but not all, as the update direction on some clients may hinder others after they are aggregated. Second, it is lacking with respect to the efficiency perspective concerning communication costs during FL and large model sizes. This paper proposes a new technical solution that utilizes network pruning on client models and aggregates the pruned models. This method enables local models to be tailored to their respective data distribution and mitigate the data heterogeneity present in agri-food data. Moreover, it allows for more compact models that consume less data during transmission. We experiment with a soybean yield forecasting dataset and find that this approach can improve inference performance by 15.5% to 20% compared to FedAvg, while reducing local model sizes by up to 84% and the data volume communicated between the clients and the server by 57.1% to 64.7%. Our method demonstrates the potential to use efficient models that are more environmentally friendly to support the agri-food sector’s transition to net zero. Future enhancements of this method could further optimize distributed learning in agri-food, enhancing sustainability and applicability.
Original language | English |
---|---|
Article number | 122847 |
Pages (from-to) | 1-12 |
Number of pages | 12 |
Journal | Expert Systems with Applications |
Volume | 242 |
Early online date | 7 Dec 2023 |
DOIs | |
Publication status | E-pub ahead of print - 7 Dec 2023 |
Bibliographical note
The work described here was funded by the EPSRC ‘Enhancing Agri-Food Transparent Sustainability’ (EATS) project, United Kingdom (grant number: EP/V042270/1) and by a University of Aberdeen Ph.D. studentship, United Kingdom. We also thank the University of Aberdeen’s HPC facility Maxwell.Open Access via the Elsevier Agreement
Data Availability Statement
All datasets used in this paper are openly available via the original sources.Keywords
- Federated Learning
- Pruning
- Deep Learning
- yield forecasting
Fingerprint
Dive into the research topics of 'Model pruning enables localized and efficient federated learning for yield forecasting and data sharing'. Together they form a unique fingerprint.Equipment
-
"Maxwell" HPC for Research
Katie Wilde (Manager) & Andrew Phillips (Manager)
Research Facilities: Facility