In this paper, we consider a federated learning (FL)-assisted fifth-generation (5G) resource block (RB) allocation scheme for terrestrial users. Enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC) users calculate their possible achievable uplink data rate with its local neural engine based on underlying channel conditions and packet availability at their data queue. Each user conveys this information to the 5G base station (BS), which then allocates the RB to the user that best meets its service requirements, thereby improving the network throughput. Each user trains its neural engine with either baseline clustered FL or our proposed peer-to-peer (P2P) FL. In clustered FL, clients are grouped by local model similarity, implicitly capturing user types such as eMBB, URLLC, and mMTC. In our P2P FL scheme, clients update their models through exchanges with similarity-selected peers, using similarity-adaptive weights. Simulation results demonstrate the effectiveness of our proposed FL approaches in scheduling users for transmission over conventional baseline schemes.

This paper presents bilevel-optimized clustered and distributed federated learning approaches, secured by blockchain technology, to enhance the predictive performance and security of collaborative building energy forecasting. Our clustered and peer-to-peer communication mechanism allows clients with similar locally trained models, implicitly reflecting similar data distributions, to collaborate more effectively without exchanging raw data. Furthermore, by leveraging blockchain’s decentralized and tamper-proof architecture, the proposed system ensures secure coordination and traceable model updates among clients without relying on a central server. Experimental results on real-world building energy datasets show that our approach effectively reduces prediction error while preserving data privacy.

This paper discusses the key challenges and future research directions for privacy-preserving federated learning (PPFL), with a focus on its application to large-scale scientific artificial intelligence models, in particular, foundation models (FMs). PPFL enables collaborative model training across distributed datasets while preserving privacy—an important collaborative approach for science. We discuss the need for efficient and scalable algorithms to address the increasing complexity of FMs, particularly when dealing with heterogeneous clients. In addition, we underscore the need for developing advance privacy-preserving techniques, such as differential privacy, to balance privacy and utility in large FMs emphasizing fairness and incentive mechanisms to ensure equitable participation among heterogeneous clients. Finally, we emphasize the need for a robust software stack supporting scalable and secure PPFL deployments across multiple high-performance computing facilities. We envision that PPFL would play a crucial role to advance scientific discovery and enable large-scale, privacy-aware collaborations across science domains.

Fast screening of drug molecules based on the ligand binding affinity is an important step in the drug discovery pipeline. Graph neural fingerprint is a promising method for developing molecular docking surrogates with high throughput and great fidelity. In this study, we built a COVID-19 drug docking dataset of about 300,000 drug candidates on 23 coronavirus protein targets. With this dataset, we trained graph neural fin-gerprint docking models for high-throughput virtual COVID-19 drug screening. The graph neural fingerprint models yield high prediction accuracy on docking scores with the mean squared error lower than 0.21 kcal/mol for most of the docking targets, showing significant improvement over conventional circular fin-gerprint methods. To make the neural fingerprints transferable for unknown targets, we also propose a transferable graph neural fingerprint method trained on multiple targets. With comparable accuracy to target-specific graph neural fingerprint models, the training and data efficiency of the transferable model is several times higher. We highlight that the impact of this study extends beyond COVID-19 dataset, as our approach for fast virtual ligand screening can be easily adapted and integrated into a general machine learning-accelerated pipeline to battle future bio-threats.

We describe a learning procedure enhancing L1-penalized regression by adding dynamically generated rules describing multidimensional “box” sets. Our rule-adding procedure is based on the classical column generation method for high-dimensional linear programming. The pricing problem for our column generation procedure reduces to the NP-hard rectangular maximum agreement (RMA) problem of finding a box that best discriminates between two weighted datasets. We solve this problem exactly using a parallel branch-and-bound procedure. The resulting rule-enhanced regression procedure is computation-intensive, but has promising prediction performance.