arXiv subjects

Dimitris Chatzopoulos

Publications and source records attributed to Dimitris Chatzopoulos.

15 recordsLinked to original sources

arXiv2025

Maximizing the efficiency of human feedback in AI alignment: a comparative analysis

Reinforcement Learning from Human Feedback (RLHF) relies on preference modeling to align machine learning systems with human values, yet the popular approach of random pair sampling with Bradley-Terry modeling is statistically limited and inefficient under constrained annotation budgets. In this work, we explore alternative sampling and evaluation strategies for preference inference in RLHF, drawing inspiration from areas such as game theory, statistics, and social choice theory. Our best-performing method, Swiss InfoGain, employs a Swiss tournament system with a proxy mutual-information-gain pairing rule, which significantly outperforms all other methods in constrained annotation budgets while also being more sample-efficient. Even in high-resource settings, we can identify superior alternatives to the Bradley-Terry baseline. Our experiments demonstrate that adaptive, resource-aware strategies reduce redundancy, enhance robustness, and yield statistically significant improvements in preference learning, highlighting the importance of balancing alignment quality with human workload in RLHF pipelines.

cs.HC↗

arXiv2024

Workflow Optimization for Parallel Split Learning

Split learning (SL) has been recently proposed as a way to enable resource-constrained devices to train multi-parameter neural networks (NNs) and participate in federated learning (FL). In a nutshell, SL splits the NN model into parts, and allows clients (devices) to offload the largest part as a processing task to a computationally powerful helper. In parallel SL, multiple helpers can process model parts of one or more clients, thus, considerably reducing the maximum training time over all clients (makespan). In this paper, we focus on orchestrating the workflow of this operation, which is critical in highly heterogeneous systems, as our experiments show. In particular, we formulate the joint problem of client-helper assignments and scheduling decisions with the goal of minimizing the training makespan, and we prove that it is NP-hard. We propose a solution method based on the decomposition of the problem by leveraging its inherent symmetry, and a second one that is fully scalable. A wealth of numerical evaluations using our testbed's measurements allow us to build a solution strategy comprising these methods. Moreover, we show that this strategy finds a near-optimal solution, and achieves a shorter makespan than the baseline scheme by up to 52.3%.

cs.DC↗

arXiv2024

MP-SL: Multihop Parallel Split Learning

Federated Learning (FL) stands out as a widely adopted protocol facilitating the training of Machine Learning (ML) models while maintaining decentralized data. However, challenges arise when dealing with a heterogeneous set of participating devices, causing delays in the training process, particularly among devices with limited resources. Moreover, the task of training ML models with a vast number of parameters demands computing and memory resources beyond the capabilities of small devices, such as mobile and Internet of Things (IoT) devices. To address these issues, techniques like Parallel Split Learning (SL) have been introduced, allowing multiple resource-constrained devices to actively participate in collaborative training processes with assistance from resourceful compute nodes. Nonetheless, a drawback of Parallel SL is the substantial memory allocation required at the compute nodes, for instance training VGG-19 with 100 participants needs 80 GB. In this paper, we introduce Multihop Parallel SL (MP-SL), a modular and extensible ML as a Service (MLaaS) framework designed to facilitate the involvement of resource-constrained devices in collaborative and distributed ML model training. Notably, to alleviate memory demands per compute node, MP-SL supports multihop Parallel SL-based training. This involves splitting the model into multiple parts and utilizing multiple compute nodes in a pipelined manner. Extensive experimentation validates MP-SL's capability to handle system heterogeneity, demonstrating that the multihop configuration proves more efficient than horizontally scaled one-hop Parallel SL setups, especially in scenarios involving more cost-effective compute nodes.

cs.LG↗

arXiv2023

Lightweight Modeling of User Context Combining Physical and Virtual Sensor Data

The multitude of data generated by sensors available on users' mobile devices, combined with advances in machine learning techniques, support context-aware services in recognizing the current situation of a user (i.e., physical context) and optimizing the system's personalization features. However, context-awareness performances mainly depend on the accuracy of the context inference process, which is strictly tied to the availability of large-scale and labeled datasets. In this work, we present a framework developed to collect datasets containing heterogeneous sensing data derived from personal mobile devices. The framework has been used by 3 voluntary users for two weeks, generating a dataset with more than 36K samples and 1331 features. We also propose a lightweight approach to model the user context able to efficiently perform the entire reasoning process on the user mobile device. To this aim, we used six dimensionality reduction techniques in order to optimize the context classification. Experimental results on the generated dataset show that we achieve a 10x speed up and a feature reduction of more than 90% while keeping the accuracy loss less than 3%.

cs.LG↗

arXiv2023

AVeCQ: Anonymous Verifiable Crowdsourcing with Worker Qualities

In crowdsourcing systems, requesters publish tasks, and interested workers provide answers to get rewards. Worker anonymity motivates participation since it protects their privacy. Anonymity with unlinkability is an enhanced version of anonymity because it makes it impossible to ``link'' workers across the tasks they participate in. Another core feature of crowdsourcing systems is worker quality which expresses a worker's trustworthiness and quantifies their historical performance. Notably, worker quality depends on the participation history, revealing information about it, while unlinkability aims to disassociate the workers' identities from their past activity. In this work, we present AVeCQ, the first crowdsourcing system that reconciles these properties, achieving enhanced anonymity and verifiable worker quality updates. AVeCQ relies on a suite of cryptographic tools, such as zero-knowledge proofs, to (i) guarantee workers' privacy, (ii) prove the correctness of worker quality scores and task answers, and (iii) commensurate payments. AVeCQ is developed modularly, where the requesters and workers communicate over a platform that supports pseudonymity, information logging, and payments. In order to compare AVeCQ with the state-of-the-art, we prototype it over Ethereum. AVeCQ outperforms the state-of-the-art in three popular crowdsourcing tasks (image annotation, average review, and Gallup polls). For instance, for an Average Review task with $5$ choices and $128$ participating workers AVeCQ is 40\% faster (including overhead to compute and verify the necessary proofs and blockchain transaction processing time) with the task's requester consuming 87\% fewer gas units.

cs.CR↗

arXiv2021

Towards Mobile Distributed Ledgers

Advances in mobile computing have paved the way for new types of distributed applications that can be executed solely by mobile devices on device-to-device (D2D) ecosystems (e.g., crowdsensing). Sophisticated applications, like cryptocurrencies, need distributed ledgers to function. Distributed ledgers, such as blockchains and directed acyclic graphs (DAGs), employ consensus protocols to add data in the form of blocks. However, such protocols are designed for resourceful devices that are interconnected via the Internet. Moreover, existing distributed ledgers are not deployable to D2D ecosystems since their storage needs are continuously increasing. In this work, we introduce and analyse Mneme, a DAG-based distributed ledger that can be maintained solely by mobile devices. Mneme utilizes two novel consensus protocols: Proof-of-Context (PoC) and Proof-of-Equivalence (PoE). PoC employs users' context to add data on Mneme. PoE is executed periodically to summarize data and produce equivalent blocks that require less storage. We analyze Mneme's security and justify the ability of PoC and PoE to guarantee the characteristics of distributed ledgers: persistence and liveness. Furthermore, we analyze potential attacks from malicious users and prove that the probability of a successful attack is inversely proportional to the square of the number of mobile users who maintain Mneme.

cs.DC↗

arXiv2021

IPLS : A Framework for Decentralized Federated Learning

The proliferation of resourceful mobile devices that store rich, multidimensional and privacy-sensitive user data motivate the design of federated learning (FL), a machine-learning (ML) paradigm that enables mobile devices to produce an ML model without sharing their data. However, the majority of the existing FL frameworks rely on centralized entities. In this work, we introduce IPLS, a fully decentralized federated learning framework that is partially based on the interplanetary file system (IPFS). By using IPLS and connecting into the corresponding private IPFS network, any party can initiate the training process of an ML model or join an ongoing training process that has already been started by another party. IPLS scales with the number of participants, is robust against intermittent connectivity and dynamic participant departures/arrivals, requires minimal resources, and guarantees that the accuracy of the trained model quickly converges to that of a centralized FL framework with an accuracy drop of less than one per thousand.

cs.NI↗

arXiv2020

SplitEasy: A Practical Approach for Training ML models on Mobile Devices

Modern mobile devices, although resourceful, cannot train state-of-the-art machine learning models without the assistance of servers, which require access to, potentially, privacy-sensitive user data. Split learning has recently emerged as a promising technique for training complex deep learning (DL) models on low-powered mobile devices. The core idea behind this technique is to train the sensitive layers of a DL model on mobile devices while offloading the computationally intensive layers to a server. Although a lot of works have already explored the effectiveness of split learning in simulated settings, a usable toolkit for this purpose does not exist. In this work, we highlight the theoretical and technical challenges that need to be resolved to develop a functional framework that trains ML models in mobile devices without transferring raw data to a server. Focusing on these challenges, we propose SplitEasy, a framework for training ML models on mobile devices using split learning. Using the abstraction provided by SplitEasy, developers can run various DL models under split learning setting by making minimal modifications. We provide a detailed explanation of SplitEasy and perform experiments with six state-of-the-art neural networks. We demonstrate how SplitEasy can train models that cannot be trained solely by a mobile device while incurring nearly constant time per data sample.

cs.LG↗

arXiv2019

Emerging Natural User Interfaces in Mobile Computing: A Bottoms-Up Survey

Mobile and wearable interfaces and interaction paradigms are highly constrained by the available screen real estate, and the computational and power resources. Although there exist many ways of displaying information to mobile users, inputting data to a mobile device is, usually, limited to a conventional touch based interaction, that distracts users from their ongoing activities. Furthermore, emerging applications, like augmented, mixed and virtual reality (AR/MR/VR), require new types of input methods in order to interact with complex virtual worlds, challenging the traditional techniques of Human-Computer Interaction (HCI). Leveraging of Natural User Interfaces (NUIs), as a paradigm of using natural intuitive actions to interact with computing systems, is one of many ways to meet these challenges in mobile computing and its modern applications. Brain-Machine Interfaces that enable thought-only hands-free interaction, Myoelectric input methods that track body gestures and gaze-tracking input interfaces - are the examples of NUIs applicable to mobile and wearable interactions. The wide adoption of wearable devices and the penetration of mobile technologies, alongside with the growing market of AR/MR/VR, motivates the exploration and implementation of new interaction paradigms. The concurrent development of bio-signal acquisition techniques and accompanying ecosystems offers a useful toolbox to address open challenges. In this survey, we present state-of-the-art bio-signal acquisition methods, summarize and evaluate recent developments in the area of NUIs and outline potential application in mobile scenarios. The survey will provide a bottoms-up overview starting from (i) underlying biological aspects and signal acquisition techniques, (ii) portable NUI hardware solutions, (iii) NUI-enabled applications, as well as (iv) research challenges and open problems.

cs.HC↗

arXiv2019

FaRM: Fair Reward Mechanism for Information Aggregation in Spontaneous Localized Settings (Extended Version)

Although peer prediction markets are widely used in crowdsourcing to aggregate information from agents, they often fail to reward the participating agents equitably. Honest agents can be wrongly penalized if randomly paired with dishonest ones. In this work, we introduce \emph{selective} and \emph{cumulative} fairness. We characterize a mechanism as fair if it satisfies both notions and present FaRM, a representative mechanism we designed. FaRM is a Nash incentive mechanism that focuses on information aggregation for spontaneous local activities which are accessible to a limited number of agents without assuming any prior knowledge of the event. All the agents in the vicinity observe the same information. FaRM uses \textit{(i)} a \emph{report strength score} to remove the risk of random pairing with dishonest reporters, \textit{(ii)} a \emph{consistency score} to measure an agent's history of accurate reports and distinguish valuable reports, \textit{(iii)} a \emph{reliability score} to estimate the probability of an agent to collude with nearby agents and prevents agents from getting swayed, and \textit{(iv)} a \emph{location robustness score} to filter agents who try to participate without being present in the considered setting. Together, report strength, consistency, and reliability represent a fair reward given to agents based on their reports.

cs.GT↗

arXiv2018

Privacy Preserving and Cost Optimal Mobile Crowdsensing using Smart Contracts on Blockchain

The popularity and applicability of mobile crowdsensing applications are continuously increasing due to the widespread of mobile devices and their sensing and processing capabilities. However, we need to offer appropriate incentives to the mobile users who contribute their resources and preserve their privacy. Blockchain technologies enable semi-anonymous multi-party interactions and can be utilized in crowdsensing applications to maintain the privacy of the mobile users while ensuring first-rate crowdsensed data. In this work, we propose to use blockchain technologies and smart contracts to orchestrate the interactions between mobile crowdsensing providers and mobile users for the case of spatial crowdsensing, where mobile users need to be at specific locations to perform the tasks. Smart contracts, by operating as processes that are executed on the blockchain, are used to preserve users' privacy and make payments. Furthermore, for the assignment of the crowdsensing tasks to the mobile users, we design a truthful, cost-optimal auction that minimizes the payments from the crowdsensing providers to the mobile users. Extensive experimental results show that the proposed privacy preserving auction outperforms state-of-the-art proposals regarding cost by ten times for high numbers of mobile users and tasks.

cs.GT↗

arXiv2018

Boosting the Performance of Content Centric Networking using Delay Tolerant Networking Mechanisms

Content-centric networking (CCN) introduces a paradigm shift from a host centric to an information centric communication model for future Internet architectures. It supports the retrieval of a particular content regardless of the physical location of the content. Content caching and content delivery networks are the most popular approaches to deal with the inherent issues of content delivery on the Internet that are caused by its design. Moreover, intermittently connected mobile environments or disruptive networks present a significant challenge to CCN deployment. In this paper, we consider the possibility of using mobile users in improving the efficiency of content delivery. Mobile users are producing a significant fraction of the total Internet traffic, and modern mobile devices have enough storage to cache the downloaded content that may interest other mobile users for a short period too. We present an analytical model of the CCN framework that integrates a delay tolerant networking architecture into the native CCN, and we present large-scale simulation results. Caching on mobile devices can improve the content retrieval time by more than 50%, while the fraction of the requests that are delivered from other mobile devices can be more than 75% in many cases.

cs.NI↗

arXiv2017

LocalCoin: An Ad-hoc Payment Scheme for Areas with High Connectivity

The popularity of digital currencies, especially cryptocurrencies, has been continuously growing since the appearance of Bitcoin. Bitcoin's security lies in a proof-of-work scheme, which requires high computational resources at the miners. Despite advances in mobile technology, existing cryptocurrencies cannot be maintained by mobile devices due to their low processing capabilities. Mobile devices can only accommodate mobile applications (wallets) that allow users to exchange credits of cryptocurrencies. In this work, we propose LocalCoin, an alternative cryptocurrency that requires minimal computational resources, produces low data traffic and works with off-the-shelf mobile devices. LocalCoin replaces the computational hardness that is at the root of Bitcoin's security with the social hardness of ensuring that all witnesses to a transaction are colluders. Localcoin features (i) a lightweight proof-of-work scheme and (ii) a distributed blockchain. We analyze LocalCoin for double spending for passive and active attacks and prove that under the assumption of sufficient number of users and properly selected tuning parameters the probability of double spending is close to zero. Extensive simulations on real mobility traces, realistic urban settings, and random geometric graphs show that the probability of success of one transaction converges to 1 and the probability of the success of a double spending attempt converges to 0.

cs.CR↗

arXiv2016

Keep Your Nice Friends Close, but Your Rich Friends Closer -- Computation Offloading Using NFC

The increasing complexity of smartphone applications and services necessitate high battery consumption but the growth of smartphones' battery capacity is not keeping pace with these increasing power demands. To overcome this problem, researchers gave birth to the Mobile Cloud Computing (MCC) research area. In this paper we advance on previous ideas, by proposing and implementing the first known Near Field Communication (NFC)-based computation offloading framework. This research is motivated by the advantages of NFC's short distance communication, with its better security, and its low battery consumption. We design a new NFC communication protocol that overcomes the limitations of the default protocol; removing the need for constant user interaction, the one-way communication restraint, and the limit on low data size transfer. We present experimental results of the energy consumption and the time duration of two computationally intensive representative applications: (i) RSA key generation and encryption, and (ii) gaming/puzzles. We show that when the helper device is more powerful than the device offloading the computations, the execution time of the tasks is reduced. Finally, we show that devices that offload application parts considerably reduce their energy consumption due to the low-power NFC interface and the benefits of offloading.

cs.NI↗

arXiv2013

Mobile augmented reality survey: a bottom-up approach

Augmented Reality (AR) is becoming mobile. Mobile devices have many constraints but also rich new features that traditional desktop computers do not have. There are several survey papers on AR, but none is dedicated to Mobile Augmented Reality (MAR). Our work serves the purpose of closing this gap. The contents are organized with a bottom-up approach. We first present the state-of-the-art in system components including hardware platforms, software frameworks and display devices, follows with enabling technologies such as tracking and data management. We then survey the latest technologies and methods to improve run-time performance and energy efficiency for practical implementation. On top of these, we further introduce the application fields and several typical MAR applications. Finally we conclude the survey with several challenge problems, which are under exploration and require great research efforts in the future.

cs.GR↗