Nicholas Donald Lane
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nicholas Donald Lane has a total of 195 co-authors. Here are the top co-authors by number of shared publications:
- Stylianos I. Venieris
Samsung AI Center Cambridge UK
11 shared publications Stefanos Laskaridis
Flower Labs Samsung AI UK University of Cambridge UK
6 shared publications- Shangguang Wang
Beijing University of Posts and Telecommunications
5 shared publications - Łukasz Dudziak
Samsung AI Center Cambridge
5 shared publications - Akhil Mathur
Nokia Bell Labs, Cambridge, United Kingdom
4 shared publications - Hongkai Wen
University of Warwick, Coventry, United Kingdom
4 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 22520-22535
FeS: Federated NLP in Few-Shot Scenarios
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 22520-22535
FeS: Federated NLP in Few-Shot Scenarios
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1630-1646
Floe : Federated Specialization for Real-Time LLM–SLM Inference
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1630-1646
Floe : Federated Specialization for Real-Time LLM–SLM Inference
- Open Access
Tina: A diffusion neural network for generating personalized AI models from text prompts
- 10 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12735-12749
FwdLLM+: Accelerating Forward-Only FedLLM With Low-Rank Perturbations
Federated Learning (FL) facilitates privacy-preserving fine-tuning of Large Language Models (LLMs) for mobile applications, termed FedLLM. A vital challenge of FedLLM is the tension between LLM complexity and resource constraint of mobile devices. In response to this challenge, we first introduce FwdLLM (our conference version), an innovative FL framework designed to enhance the FedLLM efficiency. The key idea of FwdLLM is to employ backpropagation (BP)-free training methods, requiring devices only to execute memory-efficient “perturbed inference”. Enabled by mobile NPU acceleration and an expanded array of participating devices, FwdLLM delivers substantially better wall-clock efficiency than BP-based FedLLM. However, FwdLLM based on vanilla BP-free optimization theoretically requires more optimization steps to converge. In this work, we further enhance FwdLLM to FwdLLM+, which incorporates advanced zeroth-order optimization techniques and low-rank perturbation decomposition to reduce convergence steps. Finally, we conduct extensive experiments on 4 models (ranging from 110 M to 7B) and 8 more datasets, demonstrating that FwdLLM+ achieves up to 151× faster training, a 93$\%$ memory reduction compared to vanilla BP-based FedLLM, and superior performance compared to FwdLLM, enabling efficient federated fine-tuning of billion-parameter LLMs on commodity mobile devices.
- 10 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12735-12749
FwdLLM+: Accelerating Forward-Only FedLLM With Low-Rank Perturbations
Federated Learning (FL) facilitates privacy-preserving fine-tuning of Large Language Models (LLMs) for mobile applications, termed FedLLM. A vital challenge of FedLLM is the tension between LLM complexity and resource constraint of mobile devices. In response to this challenge, we first introduce FwdLLM (our conference version), an innovative FL framework designed to enhance the FedLLM efficiency. The key idea of FwdLLM is to employ backpropagation (BP)-free training methods, requiring devices only to execute memory-efficient “perturbed inference”. Enabled by mobile NPU acceleration and an expanded array of participating devices, FwdLLM delivers substantially better wall-clock efficiency than BP-based FedLLM. However, FwdLLM based on vanilla BP-free optimization theoretically requires more optimization steps to converge. In this work, we further enhance FwdLLM to FwdLLM+, which incorporates advanced zeroth-order optimization techniques and low-rank perturbation decomposition to reduce convergence steps. Finally, we conduct extensive experiments on 4 models (ranging from 110 M to 7B) and 8 more datasets, demonstrating that FwdLLM+ achieves up to 151× faster training, a 93$\%$ memory reduction compared to vanilla BP-based FedLLM, and superior performance compared to FwdLLM, enabling efficient federated fine-tuning of billion-parameter LLMs on commodity mobile devices.
- Open Access
- 21 February 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Auditing unauthorized training data from AI generated content using information isotopes
The rapid growth of AI systems has been fueled by large-scale human data, intensifying concerns over the unauthorized use of intellectual property and privacy-sensitive content during model training. Auditing such misuse is particularly challenging since mainstream AI services operate as black boxes, exposing only generated outputs while concealing their training and inference processes. In this work, inspired by chemical isotope tracing, we introduce the concept of information isotopes to trace training data within opaque AI systems. We propose an information-isotope tracing framework that selectively marks target data elements and detects their propagation in model outputs, providing concrete evidence of data utilization under black-box access. Experiments on thirteen AI models across six datasets demonstrate that our method distinguishes training from non-training data with up to 99% accuracy and strong statistical significance (p < 0.01) using approximately 4,000 words of evidence. An open-source tool is released to support practical data rights protection.
- 21 February 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessAuditing unauthorized training data from AI generated content using information isotopes
The rapid growth of AI systems has been fueled by large-scale human data, intensifying concerns over the unauthorized use of intellectual property and privacy-sensitive content during model training. Auditing such misuse is particularly challenging since mainstream AI services operate as black boxes, exposing only generated outputs while concealing their training and inference processes. In this work, inspired by chemical isotope tracing, we introduce the concept of information isotopes to trace training data within opaque AI systems. We propose an information-isotope tracing framework that selectively marks target data elements and detects their propagation in model outputs, providing concrete evidence of data utilization under black-box access. Experiments on thirteen AI models across six datasets demonstrate that our method distinguishes training from non-training data with up to 99% accuracy and strong statistical significance (p < 0.01) using approximately 4,000 words of evidence. An open-source tool is released to support practical data rights protection.
- Open Access
Floe: Federated Specialization for Real-Time LLM-SLM Inference
Deploying large language models (LLMs) in real-time systems remains challenging due to their substantial computational demands and privacy concerns. We propose Floe, a hybrid federated learning framework designed for latency-sensitive, resource-constrained environments. Floe combines a cloud-based black-box LLM with lightweight small language models (SLMs) on edge devices to enable low-latency, privacy-preserving inference. Personal data and fine-tuning remain on-device, while the cloud LLM contributes general knowledge without exposing proprietary weights. A heterogeneity-aware LoRA adaptation strategy enables efficient edge deployment across diverse hardware, and a logit-level fusion mechanism enables real-time coordination between edge and cloud models. Extensive experiments demonstrate that Floe enhances user privacy and personalization. Moreover, it significantly improves model performance and reduces inference latency on edge devices under real-time constraints compared with baseline approaches.
Open AccessFloe: Federated Specialization for Real-Time LLM-SLM Inference
Deploying large language models (LLMs) in real-time systems remains challenging due to their substantial computational demands and privacy concerns. We propose Floe, a hybrid federated learning framework designed for latency-sensitive, resource-constrained environments. Floe combines a cloud-based black-box LLM with lightweight small language models (SLMs) on edge devices to enable low-latency, privacy-preserving inference. Personal data and fine-tuning remain on-device, while the cloud LLM contributes general knowledge without exposing proprietary weights. A heterogeneity-aware LoRA adaptation strategy enables efficient edge deployment across diverse hardware, and a logit-level fusion mechanism enables real-time coordination between edge and cloud models. Extensive experiments demonstrate that Floe enhances user privacy and personalization. Moreover, it significantly improves model performance and reduces inference latency on edge devices under real-time constraints compared with baseline approaches.
- Open Access
FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are independent and identically distributed (IID). However, when this assumption does not hold, the global model accuracy may drop significantly, limiting FL applicability in real-world scenarios. To address this gap, we propose FLUX, a novel clustering-based FL (CFL) framework that addresses the four most common types of distribution shifts during both training and test time. To this end, FLUX leverages privacy-preserving client-side descriptor extraction and unsupervised clustering to ensure robust performance and scalability across varying levels and types of distribution shifts. Unlike existing CFL methods addressing non-IID client distribution shifts, FLUX i) does not require any prior knowledge of the types of distribution shifts or the number of client clusters, and ii) supports test-time adaptation, enabling unseen and unlabeled clients to benefit from the most suitable cluster-specific models. Extensive experiments across four standard benchmarks, two real-world datasets and ten state-of-the-art baselines show that FLUX improves performance and stability under diverse distribution shifts, achieving an average accuracy gain of up to 23 percentage points over the best-performing baselines, while maintaining computational and communication overhead comparable to FedAvg.
Open AccessFLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are independent and identically distributed (IID). However, when this assumption does not hold, the global model accuracy may drop significantly, limiting FL applicability in real-world scenarios. To address this gap, we propose FLUX, a novel clustering-based FL (CFL) framework that addresses the four most common types of distribution shifts during both training and test time. To this end, FLUX leverages privacy-preserving client-side descriptor extraction and unsupervised clustering to ensure robust performance and scalability across varying levels and types of distribution shifts. Unlike existing CFL methods addressing non-IID client distribution shifts, FLUX i) does not require any prior knowledge of the types of distribution shifts or the number of client clusters, and ii) supports test-time adaptation, enabling unseen and unlabeled clients to benefit from the most suitable cluster-specific models. Extensive experiments across four standard benchmarks, two real-world datasets and ten state-of-the-art baselines show that FLUX improves performance and stability under diverse distribution shifts, achieving an average accuracy gain of up to 23 percentage points over the best-performing baselines, while maintaining computational and communication overhead comparable to FedAvg.
- Open Access
Bringing Federated Learning to Space
As Low Earth Orbit (LEO) satellite constellations rapidly expand to hundreds and thousands of spacecraft, the need for distributed on-board machine learning becomes critical to address downlink bandwidth limitations. Federated learning (FL) offers a promising framework to conduct collaborative model training across satellite networks. Realizing its benefits in space naturally requires addressing space-specific constraints, from intermittent connectivity to dynamics imposed by orbital motion. This work presents the first systematic feasibility analysis of adapting off-the-shelf FL algorithms for satellite constellation deployment. We introduce a comprehensive "space-ification" framework that adapts terrestrial algorithms (FedAvg, FedProx, FedBuff) to operate under orbital constraints, producing an orbital-ready suite of FL algorithms. We then evaluate these space-ified methods through extensive parameter sweeps across 768 constellation configurations that vary cluster sizes (1-10), satellites per cluster (1-10), and ground station networks (1-13). Our analysis demonstrates that space-adapted FL algorithms efficiently scale to constellations of up to 100 satellites, achieving performance close to the centralized ideal. Multi-month training cycles can be reduced to days, corresponding to a 9x speedup through orbital scheduling and local coordination within satellite clusters. These results provide actionable insights for future mission designers, enabling distributed on-board learning for more autonomous, resilient, and data-driven satellite operations.
Open AccessBringing Federated Learning to Space
As Low Earth Orbit (LEO) satellite constellations rapidly expand to hundreds and thousands of spacecraft, the need for distributed on-board machine learning becomes critical to address downlink bandwidth limitations. Federated learning (FL) offers a promising framework to conduct collaborative model training across satellite networks. Realizing its benefits in space naturally requires addressing space-specific constraints, from intermittent connectivity to dynamics imposed by orbital motion. This work presents the first systematic feasibility analysis of adapting off-the-shelf FL algorithms for satellite constellation deployment. We introduce a comprehensive "space-ification" framework that adapts terrestrial algorithms (FedAvg, FedProx, FedBuff) to operate under orbital constraints, producing an orbital-ready suite of FL algorithms. We then evaluate these space-ified methods through extensive parameter sweeps across 768 constellation configurations that vary cluster sizes (1-10), satellites per cluster (1-10), and ground station networks (1-13). Our analysis demonstrates that space-adapted FL algorithms efficiently scale to constellations of up to 100 satellites, achieving performance close to the centralized ideal. Multi-month training cycles can be reduced to days, corresponding to a 9x speedup through orbital scheduling and local coordination within satellite clusters. These results provide actionable insights for future mission designers, enabling distributed on-board learning for more autonomous, resilient, and data-driven satellite operations.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1659-1670
FedGuCci: Making Local Models More Connected in Landscape for Federated Learning
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1659-1670
Open AccessFedGuCci: Making Local Models More Connected in Landscape for Federated Learning
- Open Access
- 19 June 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-12
Ubiquitous memory augmentation via mobile multimodal embedding system
Forgetting is inevitable in human memory. Recently, multimodal embedding models have been proposed to vectorize multimodal reality into a unified embedding space. Once generated, these embeddings allow mobile users to quickly retrieve relevant information, effectively augmenting their memory. However, as the model’s capacity increases, its resource consumption also rises. The resulting slow throughput and significant computational resource requirements hinder its deployment on mobile devices. In this paper, we present Reminisce, an efficient on-device multimodal embedding system that enables high-throughput embedding and precise retrieval on resource-constrained mobile devices. The core design draws inspiration from the memory functions of the human brain, utilizing coarse-grained embeddings to identify likely candidates, which are then refined through query-driven fine-grained retrieval. A series of algorithm-hardware orchestrated optimizations automatically navigates this process and strengthen the embedding quality. Experiments show that Reminisce provides high-quality embedding representation with high throughput while operating silently in the background with negligible memory usage and reduced energy consumption.
- 19 June 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-12
Open AccessUbiquitous memory augmentation via mobile multimodal embedding system
Forgetting is inevitable in human memory. Recently, multimodal embedding models have been proposed to vectorize multimodal reality into a unified embedding space. Once generated, these embeddings allow mobile users to quickly retrieve relevant information, effectively augmenting their memory. However, as the model’s capacity increases, its resource consumption also rises. The resulting slow throughput and significant computational resource requirements hinder its deployment on mobile devices. In this paper, we present Reminisce, an efficient on-device multimodal embedding system that enables high-throughput embedding and precise retrieval on resource-constrained mobile devices. The core design draws inspiration from the memory functions of the human brain, utilizing coarse-grained embeddings to identify likely candidates, which are then refined through query-driven fine-grained retrieval. A series of algorithm-hardware orchestrated optimizations automatically navigates this process and strengthen the embedding quality. Experiments show that Reminisce provides high-quality embedding representation with high throughput while operating silently in the background with negligible memory usage and reduced energy consumption.