Searcharxiv⌕ Search

arXiv subjects

Stefanos Laskaridis

Publications and source records attributed to Stefanos Laskaridis.

At least 19 recordsLinked to original sources
arXiv2026

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models

Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off between accuracy and computation in an MoE model typically exhibits large discontinuities. We propose Mixture of Slimmable Experts (MoSE), an MoE architecture in which each expert has a nested, slimmable structure that can be executed at variable widths. This enables conditional computation not only over which experts are activated but also over how much of each expert is utilized. Consequently, a single pretrained MoSE model can support a more continuous spectrum of accuracy-compute trade-offs at inference time. We present a simple and stable training recipe for slimmable experts under sparse routing, combining multi-width training with standard MoE objectives. During inference, we explore strategies for runtime width determination, including a lightweight test-time training mechanism that learns how to map router confidence/probabilities to expert widths under a fixed budget. Experiments on GPT-style models, various routing regimes, zero-shot downstream reasoning benchmarks, and continual pre-training adaptation of DeepSeek model show that MoSE matches or improves standard MoE at full width and consistently shifts the compute-quality frontier toward lower inference FLOPs. The code can be found at: https://github.com/tnurbek/mose.

cs.LG↗
arXiv2026

FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment

The growing scale of deep neural networks, encompassing large language models (LLMs) and vision transformers (ViTs), has made training from scratch prohibitively expensive and deployment increasingly costly. These models are often used as computational monoliths with fixed cost, hindering adaptive deployment across different cost budgets. We argue that nested components, ordered by importance, can be extracted from pretrained models and selectively activated within the available computational budget. To this end, our proposed FlexRank method leverages low-rank weight decomposition with nested, importance-based consolidation to extract submodels of increasing capabilities. Our approach enables a "train-once, deploy-everywhere" paradigm offering a graceful trade-off between cost and performance without training from scratch for each budget - advancing practical deployment of large models.

cs.LG↗
arXiv2026

LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning

Large pre-trained models are commonly adapted to downstream tasks using parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA), which injects small trainable low-rank matrices instead of updating all weights. While LoRA dramatically reduces trainable parameters with little overhead, it can still underperform full fine-tuning in accuracy and often converges more slowly. We introduce LoFT, a novel low-rank adaptation method that behaves like full fine-tuning by aligning the optimizer's internal dynamics with those of updating all model weights. LoFT not only learns weight updates in a low-rank subspace (like LoRA) but also properly projects the optimizer's first and second moments (Adam's momentum and variance) into the same subspace, mirroring full-model updates. By aligning the low-rank update itself with the full update, LoFT eliminates the need for tuning extra hyperparameters, e.g., the LoRA scaling factor $α$. Empirically, this approach substantially narrows the performance gap between adapter-based tuning and full fine-tuning and consistently outperforms standard LoRA-style methods, all without increasing inference cost.

cs.LG↗
arXiv2025

NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation

Large Language Models (LLM) are typically trained on vast amounts of data from various sources. Even when designed modularly (e.g., Mixture-of-Experts), LLMs can leak privacy on their sources. Conversely, training such models in isolation arguably prohibits generalization. To this end, we propose a framework, NoEsis, which builds upon the desired properties of modularity, privacy, and knowledge transfer. NoEsis integrates differential privacy with a hybrid two-staged parameter-efficient fine-tuning that combines domain-specific low-rank adapters, acting as experts, with common prompt tokens, acting as a knowledge-sharing backbone. Results from our evaluation on CodeXGLUE showcase that NoEsis can achieve provable privacy guarantees with tangible knowledge transfer across domains, and empirically show protection against Membership Inference Attacks. Finally, on code completion tasks, NoEsis bridges at least 77% of the accuracy gap between the non-shared and the non-private baseline.

cs.CR↗
arXiv2024

MELTing point: Mobile Evaluation of Language Transformers

Transformers have revolutionized the machine learning landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being broadly deployed on mobile. As personal devices become increasingly powerful and prompt privacy becomes an ever more pressing issue, we explore the current state of mobile execution of Large Language Models (LLMs). To achieve this, we have created our own automation infrastructure, MELT, which supports the headless execution and benchmarking of LLMs on device, supporting different models, devices and frameworks, including Android, iOS and Nvidia Jetson devices. We evaluate popular instruction fine-tuned LLMs and leverage different frameworks to measure their end-to-end and granular performance, tracing their memory and energy requirements along the way. Our analysis is the first systematic study of on-device LLM execution, quantifying performance, energy efficiency and accuracy across various state-of-the-art models and showcases the state of on-device intelligence in the era of hyperscale models. Results highlight the performance heterogeneity across targets and corroborates that LLM inference is largely memory-bound. Quantization drastically reduces memory requirements and renders execution viable, but at a non-negligible accuracy cost. Drawing from its energy footprint and thermal behavior, the continuous execution of LLMs remains elusive, as both factors negatively affect user experience. Last, our experience shows that the ecosystem is still in its infancy, and algorithmic as well as hardware breakthroughs can significantly shift the execution cost. We expect NPU acceleration, and framework-hardware co-design to be the biggest bet towards efficient standalone execution, with the alternative of offloading tailored towards edge deployments.

cs.LG↗
arXiv2024

The Future of Consumer Edge-AI Computing

In the last decade, Deep Learning has rapidly infiltrated the consumer end, mainly thanks to hardware acceleration across devices. However, as we look towards the future, it is evident that isolated hardware will be insufficient. Increasingly complex AI tasks demand shared resources, cross-device collaboration, and multiple data types, all without compromising user privacy or quality of experience. To address this, we introduce a novel paradigm centered around EdgeAI-Hub devices, designed to reorganise and optimise compute resources and data access at the consumer edge. To this end, we lay a holistic foundation for the transition from on-device to Edge-AI serving systems in consumer environments, detailing their components, structure, challenges and opportunities.

cs.LG↗
arXiv2024

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition

Deep Neural Networks (DNNs) have been a large driver for AI breakthroughs in recent years. However, these models have been getting increasingly large as they become more accurate and safe. This means that their training becomes increasingly costly and time-consuming and typically yields a single model to fit all targets. Various techniques have been proposed in the literature to mitigate this, including pruning, sparsification, or quantization of model weights and updates. While achieving high compression rates, they often incur significant computational overheads at training or lead to non-negligible accuracy penalty. Alternatively, factorization methods have been leveraged for low-rank compression of DNNs. Similarly, such techniques (e.g., SVD) frequently rely on heavy iterative decompositions of layers and are potentially sub-optimal for non-linear models, such as DNNs. We take a further step in designing efficient low-rank models and propose Maestro, a framework for trainable low-rank layers. Instead of iteratively applying a priori decompositions, the low-rank structure is baked into the training process through LoD, a low-rank ordered decomposition. Not only is this the first time importance ordering via sampling is applied on the decomposed DNN structure, but it also allows selecting ranks at a layer granularity. Our theoretical analysis demonstrates that in special cases LoD recovers the SVD decomposition and PCA. Applied to DNNs, Maestro enables the extraction of lower footprint models that preserve performance. Simultaneously, it enables the graceful trade-off between accuracy-latency for deployment to even more constrained devices without retraining.

cs.LG↗
arXiv2024

Recurrent Early Exits for Federated Learning with Heterogeneous Clients

Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clients with varying hardware capacities; clients have differing compute and memory requirements. To tackle this challenge, recent state-of-the-art approaches leverage the use of early exits. Nonetheless, these approaches fall short of mitigating the challenges of joint learning multiple exit classifiers, often relying on hand-picked heuristic solutions for knowledge distillation among classifiers and/or utilizing additional layers for weaker classifiers. In this work, instead of utilizing multiple classifiers, we propose a recurrent early exit approach named ReeFL that fuses features from different sub-models into a single shared classifier. Specifically, we use a transformer-based early-exit module shared among sub-models to i) better exploit multi-layer feature representations for task-specific prediction and ii) modulate the feature representation of the backbone model for subsequent predictions. We additionally present a per-client self-distillation approach where the best sub-model is automatically selected as the teacher of the other sub-models at each client. Our experiments on standard image and speech classification benchmarks across various emerging federated fine-tuning baselines demonstrate ReeFL's effectiveness over previous works.

cs.LG↗
arXiv2023

Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs

With deep neural networks (DNNs) emerging as the backbone in a multitude of computer vision tasks, their adoption in real-world applications broadens continuously. Given the abundance and omnipresence of smart devices in the consumer landscape, "smart ecosystems'' are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying centralised neural processing units (NPUs) at the edge, where multiple devices (e.g. in smart homes or autonomous vehicles) can stream their data for processing with dynamic rates. While this provides enhanced potential for input batching, naive solutions can lead to subpar performance and quality of experience, especially under spiking loads. At the same time, the deployment of dynamic DNNs, comprising stochastic computation graphs (e.g. early-exit (EE) models), introduces a new dimension of dynamic behaviour in such systems. In this work, we propose a novel early-exit-aware scheduling algorithm that allows sample preemption at run time, to account for the dynamicity introduced both by the arrival and early-exiting processes. At the same time, we introduce two novel dimensions to the design space of the NPU hardware architecture, namely Fluid Batching and Stackable Processing Elements, that enable run-time adaptability to different batch sizes and significantly improve the NPU utilisation even at small batches. Our evaluation shows that the proposed system achieves an average 1.97x and 6.7x improvement over state-of-the-art DNN streaming systems in terms of average latency and tail latency service-level objective (SLO) satisfaction, respectively.

cs.LG↗
arXiv2022

Federated Learning for Inference at Anytime and Anywhere

Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication cost, robustness to heterogeneous data, and support for diverse device capabilities. However, there is no unified framework that addresses all these problems together. This paper studies the challenges and opportunities of exploiting pre-trained Transformer models in FL. In particular, we propose to efficiently adapt such pre-trained models by injecting a novel attention-based adapter module at each transformer block that both modulates the forward pass and makes an early prediction. Training only the lightweight adapter by FL leads to fast and communication-efficient learning even in the presence of heterogeneous data and devices. Extensive experiments on standard FL benchmarks, including CIFAR-100, FEMNIST and SpeechCommandsv2 demonstrate that this simple framework provides fast and accurate FL while supporting heterogenous device capabilities, efficient personalization, and scalable-cost anytime inference.

cs.LG↗
arXiv2022

FedorAS: Federated Architecture Search under system heterogeneity

Federated learning (FL) has recently gained considerable attention due to its ability to learn on decentralised data while preserving client privacy. However, it also poses additional challenges related to the heterogeneity of the participating devices, both in terms of their computational capabilities and contributed data. Meanwhile, Neural Architecture Search (NAS) has been successfully used with centralised datasets, producing state-of-the-art results in constrained or unconstrained settings. However, such centralised datasets may not be always available for training. Most recent work at the intersection of NAS and FL attempts to alleviate this issue in a cross-silo federated setting, which assumes homogeneous compute environments with datacenter-grade hardware. In this paper we explore the question of whether we can design architectures of different footprints in a cross-device federated setting, where the device landscape, availability and scale are very different. To this end, we design our system, FedorAS, to discover and train promising architectures in a resource-aware manner when dealing with devices of varying capabilities holding non-IID distributed data. We present empirical evidence of its effectiveness across different settings, spanning across three different modalities (vision, speech, text), and showcase its better performance compared to state-of-the-art federated solutions, while maintaining resource efficiency.

cs.LG↗
arXiv2022

Multi-Exit Semantic Segmentation Networks

Semantic segmentation arises as the backbone of many vision systems, spanning from self-driving cars and robot navigation to augmented reality and teleconferencing. Frequently operating under stringent latency constraints within a limited resource envelope, optimising for efficient execution becomes important. At the same time, the heterogeneous capabilities of the target platforms and the diverse constraints of different applications require the design and training of multiple target-specific segmentation models, leading to excessive maintenance costs. To this end, we propose a framework for converting state-of-the-art segmentation CNNs to Multi-Exit Semantic Segmentation (MESS) networks: specially trained models that employ parametrised early exits along their depth to i) dynamically save computation during inference on easier samples and ii) save training and maintenance cost by offering a post-training customisable speed-accuracy trade-off. Designing and training such networks naively can hurt performance. Thus, we propose a novel two-staged training scheme for multi-exit networks. Furthermore, the parametrisation of MESS enables co-optimising the number, placement and architecture of the attached segmentation heads along with the exit policy, upon deployment via exhaustive search in <1 GPUh. This allows MESS to rapidly adapt to the device capabilities and application requirements for each target use-case, offering a train-once-deploy-everywhere solution. MESS variants achieve latency gains of up to 2.83x with the same accuracy, or 5.33 pp higher accuracy for the same computational budget, compared to the original backbone network. Lastly, MESS delivers orders of magnitude faster architectural customisation, compared to state-of-the-art techniques.

cs.CV↗
arXiv2022

FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout

Federated Learning (FL) has been gaining significant traction across different ML tasks, ranging from vision to keyboard predictions. In large-scale deployments, client heterogeneity is a fact and constitutes a primary problem for fairness, training performance and accuracy. Although significant efforts have been made into tackling statistical data heterogeneity, the diversity in the processing capabilities and network bandwidth of clients, termed as system heterogeneity, has remained largely unexplored. Current solutions either disregard a large portion of available devices or set a uniform limit on the model's capacity, restricted by the least capable participants. In this work, we introduce Ordered Dropout, a mechanism that achieves an ordered, nested representation of knowledge in deep neural networks (DNNs) and enables the extraction of lower footprint submodels without the need of retraining. We further show that for linear maps our Ordered Dropout is equivalent to SVD. We employ this technique, along with a self-distillation methodology, in the realm of FL in a framework called FjORD. FjORD alleviates the problem of client system heterogeneity by tailoring the model width to the client's capabilities. Extensive evaluation on both CNNs and RNNs across diverse modalities shows that FjORD consistently leads to significant performance gains over state-of-the-art baselines, while maintaining its nested structure.

cs.LG↗
arXiv2022

DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device

Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs). To alleviate their excessive computational demands, developers have traditionally resorted to cloud offloading, inducing high infrastructure costs and a strong dependence on networking conditions. On the other end, the emergence of powerful SoCs is gradually enabling on-device execution. Nonetheless, low- and mid-tier platforms still struggle to run state-of-the-art CNNs sufficiently. In this paper, we present DynO, a distributed inference framework that combines the best of both worlds to address several challenges, such as device heterogeneity, varying bandwidth and multi-objective requirements. Key components that enable this are its novel CNN-specific data packing method, which exploits the variability of precision needs in different parts of the CNN when onloading computation, and its novel scheduler that jointly tunes the partition point and transferred data precision at run time to adapt inference to its execution environment. Quantitative evaluation shows that DynO outperforms the current state-of-the-art, improving throughput by over an order of magnitude over device-only execution and up to 7.9x over competing CNN offloading systems, with up to 60x less data transferred.

cs.DC↗
arXiv2021

Smart at what cost? Characterising Mobile Deep Neural Networks in the wild

With smartphones' omnipresence in people's pockets, Machine Learning (ML) on mobile is gaining traction as devices become more powerful. With applications ranging from visual filters to voice assistants, intelligence on mobile comes in many forms and facets. However, Deep Neural Network (DNN) inference remains a compute intensive workload, with devices struggling to support intelligence at the cost of responsiveness.On the one hand, there is significant research on reducing model runtime requirements and supporting deployment on embedded devices. On the other hand, the strive to maximise the accuracy of a task is supported by deeper and wider neural networks, making mobile deployment of state-of-the-art DNNs a moving target. In this paper, we perform the first holistic study of DNN usage in the wild in an attempt to track deployed models and match how these run on widely deployed devices. To this end, we analyse over 16k of the most popular apps in the Google Play Store to characterise their DNN usage and performance across devices of different capabilities, both across tiers and generations. Simultaneously, we measure the models' energy footprint, as a core cost dimension of any mobile deployment. To streamline the process, we have developed gaugeNN, a tool that automates the deployment, measurement and analysis of DNNs on devices, with support for different frameworks and platforms. Results from our experience study paint the landscape of deep learning deployments on smartphones and indicate their popularity across app developers. Furthermore, our study shows the gap between bespoke techniques and real-world deployments and the need for optimised deployment of deep learning models in a highly dynamic and heterogeneous ecosystem.

cs.LG↗
arXiv2021

Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions

DNNs are becoming less and less over-parametrised due to recent advances in efficient model design, through careful hand-crafted or NAS-based methods. Relying on the fact that not all inputs require the same amount of computation to yield a confident prediction, adaptive inference is gaining attention as a prominent approach for pushing the limits of efficient deployment. Particularly, early-exit networks comprise an emerging direction for tailoring the computation depth of each input sample at runtime, offering complementary performance gains to other efficiency optimisations. In this paper, we decompose the design methodology of early-exit networks to its key components and survey the recent advances in each one of them. We also position early-exiting against other efficient inference solutions and provide our insights on the current challenges and most promising future directions for research in the field.

cs.LG↗
arXiv2021

It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation

On-device machine learning is becoming a reality thanks to the availability of powerful hardware and model compression techniques. Typically, these models are pretrained on large GPU clusters and have enough parameters to generalise across a wide variety of inputs. In this work, we observe that a much smaller, personalised model can be employed to fit a specific scenario, resulting in both higher accuracy and faster execution. Nevertheless, on-device training is extremely challenging, imposing excessive computational and memory requirements even for flagship smartphones. At the same time, on-device data availability might be limited and samples are most frequently unlabelled. To this end, we introduce PersEPhonEE, a framework that attaches early exits on the model and personalises them on-device. These allow the model to progressively bypass a larger part of the computation as more personalised data become available. Moreover, we introduce an efficient on-device algorithm that trains the early exits in a semi-supervised manner at a fraction of the whole network's personalisation time. Results show that PersEPhonEE boosts accuracy by up to 15.9% while dropping the training cost by up to 2.2x and inference latency by 2.2-3.2x on average for the same accuracy, depending on the availability of labels on-device.

cs.LG↗