Abstract This paper introduces a novel approach for training generative adversarial networks using federated machine learning. Generative adversarial networks have gained plenty of attention in the research community especially with their abilities to produce high quality synthetic data for a variety of use-cases. Yet, when combined with federated learning, those models suffer from degradation in both training time and quality of results. To address this challenge, this paper introduces a novel approach that uses hierarchical learning techniques to enable the efficient training of federated GAN models. The proposed approach introduces an innovative mechanism that dynamically clusters participant clients to edge servers as well as a novel multi-generator GAN architecture that utilizes non-identical model aggregation stages. The proposed approach has been evaluated on a number of benchmark datasets to measure its performance on higher numbers of participating clients. The results show that HFL-GAN outperforms other comparative state-of-the-art approaches in the training of GAN models in complex non-IID federated learning settings.

Open market environments consist of a set of participants (vendors and consumers) that dynamically leave or join the market. As a result, the arising dynamism leads to uncertainties in supply and demand of the resources in these open markets. In specific, in such uncertain markets, vendors attempt to maximise their revenue by dynamically changing their selling prices according to the market demand. In this regard, an optimal resource allocation approach becomes immensely needed to optimise the selling prices based on the supply and demand of the resources in the open market. Therefore, optimal selling prices should maximise the revenue of vendors while protecting the utility of buyers. In this context, we propose a real-time pricing approach for resource allocation in open market environments. The proposed approach introduces a priority-based fairness mechanism to allocate the available resources in a reverse-auction paradigm. Finally, we compare the proposed approach with two state-of-the-art resource allocation approaches. The experimental results show that the proposed approach outperforms the other two resource allocation approaches in its ability to maximise the vendors’ revenue.

Existing work in physical robot caregiving is limited in its ability to provide long-term assistance. This is majorly due to (i) lack of well-defined problems, (ii) diversity of tasks, and (iii) limited access to stakeholders from the caregiving community. We propose Structuring Physically Assistive Robotics for Caregiving with Stakeholders-in-the-loop (SPARCS) to address these challenges. SPARCS is a framework for physical robot caregiving comprising (i) Building Blocks, models that define physical robot caregiving scenarios, (ii) Structured Workflows, hierarchical workflows that enable us to answer the Whats and Hows of physical robot caregiving, and (iii) SPARCS-box, a web-based platform to facilitate dialogue between all stakeholders. We collect clinical data for six care recipients with varying disabilities and demonstrate the use of SPARCS in designing well-defined caregiving scenarios and identifying their care requirements. All the data and workflows are available on SPARCS-box. We demonstrate the utility of SPARCS in building a robot-assisted feeding system for one of the care recipients. We also perform experiments to show the adaptability of this system to different caregiving scenarios. Finally, we identify open challenges in physical robot caregiving by consulting care recipients and caregivers. Supplementary material can be found at emprise.cs.cornell.edu/sparcs.

Federated learning (FL) is a promising technique for collaboratively training machine-learning models on massively distributed clients data under privacy constraints. However, the existing FL literature focuses on speeding up the learning process and ignores minimizing the communication cost which is critical for resource-constrained clients. To this end, in this article, we propose a novel 3-way hierarchical framework (THF) to promote communication efficiency in FL. Using the proposed framework, only a cluster head (CH) communicates with the cloud server through edge aggregation in order to minimize the communication cost of clients. In particular, the clients upload their local models to their respective CHs, which are responsible to forward them to the corresponding edge server. The edge server averages the local models and iterates until it achieves the edge accuracy. Afterward, each edge server uploads the edge models to the cloud server for global aggregation. In this way, model downloading and uploading requires less bandwidth due to the short distance from source to destination that makes an efficient 3-way hierarchical network structure. In addition, we formulate a joint communication and computation resource management scheme through efficient client selection in order to achieve global cost minimization in FL. We conduct extensive empirical evaluations on diverse data learning tasks on multiple data sets to signify that THF achieves global cost savings and converges within fewer communication rounds compared to other FL approaches.

In the era of advanced technologies, mobile devices are equipped with computing and sensing capabilities that gather excessive amounts of data. These amounts of data are suitable for training different learning models. Cooperated with Deep Learning (DL) advancements, these learning models empower numerous useful applications, e.g., image processing, speech recognition, healthcare, vehicular network, and many more. Traditionally, Machine Learning (ML) approaches require data to be centralised in cloud-based data-centres. However, this data is often large in quantity and privacy-sensitive, preventing logging into these data-centres for training the learning models. In turn, this results in critical issues of high latency and communication inefficiency. Recently, in light of new privacy legislation in many countries, the concept of Federated Learning (FL) has been introduced. In FL, mobile users are empowered to learn a global model by aggregating their local models without sharing the privacy-sensitive data. Usually, these mobile users have slow network connections to the data-centre where the global model is maintained. Moreover, in a complicated and extensive scale network, heterogeneous devices with various energy constraints are involved. This raises the challenge of communication cost when implementing FL at a large scale. To this end, in this research, we begin with the fundamentals of FL, and then we highlight the recent FL algorithms and evaluate their communication efficiency with detailed comparisons. Furthermore, we propose a set of solutions to alleviate the existing FL problems from a communication perspective and a privacy perspective.

Rehabilitation on a regular basis is essential to recover functional ability for patients with physical disabilities. However, performing correct movements without the therapist's guidance is considered to be a challenging problem. To this end, we propose an interactive system to support patients through rehabilitation, where a movement guidance agent is included. Our system recognizes and assists patients while engaging in rehabilitation activities. The proposed approach consists of three significant steps: (1) the estimation of patient movement through the camera; (2) the detection of patient movement; and (3) the detected movements, are then observed by an agent in order to instruct correct movement, if the movement was incorrectly performed. To this end, we propose an agent-based system that allows users to perform rehabilitation exercises anywhere with the proper guidance system. The proposed system is applied to track patient activities in real-time, with lightweight devices such as mobile phones.

Automated negotiations based on learning models have been widely applied in different domains of negotiation. Specifically, for resource allocation in decentralised open market environments with multiple vendors and multiple buyers. In such open market environments, there exists dynamically changing supply and demand of resources, with dynamic arrival of buyers in the market. Besides, each buyer has their own set of constraints, such as budget constraints, time constraints, etc. In this context, efficient negotiation policies should be capable of maintaining the equilibrium between the utilities of both the vendors and the buyers. In this research, we aim to design a mechanism for an optimal auction paradigm, considering the existence of interdependent undisclosed preferences of both, buyers and vendors. Therefore, learning-based negotiation models are immensely appropriate for such open market environments; wherein, self-interested autonomous vendors and buyers cooperate/compete to maximize their utilities based on their undisclosed preferences. Toward this end, we present our current proposal, the two-stage learning-based resource allocation mechanism, wherein utilities of vendors and buyers are optimised at each stage. We are aiming to compare our proposed learning-based resource allocation mechanism with two state-of-the-art bidding-based resource allocation mechanism, which are based on, fixed bidding policy (Samimi, Teimouri, and Mukhtar 2016) and demand-based bidding policy (Kong, Zhang, and Ye 2015). The comparison is to be done based on the overall performance of the open market environment and also based on the individual performances of vendors and buyers.

The widespread use of web services in forming complex online applications requires service composition to cope with highly dynamic and heterogeneous environments. Traditional centralized service composition techniques are not sufficient to address the needs of applications in decentralized environments. In this paper, a stigmergic-based approach is proposed to model the decentralized service interactions and handle service composition in highly dynamic open environments. In the proposed approach, web services and resources are modeled as multiple agents. Stigmergic-based self-organization mechanisms among agents are deployed to facilitate adapting service composition. In addition, to overcome the limitations of traditional QoS-based approaches, trust measurements are deployed as a criterion for service selection. To improve the performance of the proposed stigmergic-based approach under dynamic scale-free environments, we investigate the hybridization with local search operators to consolidate adaptation, and diversity schemes are introduced to facilitate continual service adaptation. Extensive experiments show the efficiency of the proposed approach in dealing with incomplete information and dynamic factors in composing and adapting web services in open environments. The experiment results also show that the proposed approach achieves a better performance than other traditional approaches.

Reinforcement learning has emerged as a powerful tool to compose and adapt Web services in open and dynamic environments. However, the most common applications of reinforcement learning algorithms are relatively inefficient in their use of experience data, which may affect the stability of the learning process. In particular, they make just one learning update for each interaction experience. This paper proposes two novel algorithms that aim to achieve greater data efficiency by saving experience data and using it in aggregate to make updates to the learned policy. The first algorithm introduces an offline learning scheme for service composition where the online learning task is transformed into a series of supervised learning steps. The second algorithm presents a coordination mechanism in order to enable multiple agents to learn the service composition task cooperatively. The results of our experiments show the effectiveness of the proposed algorithms compared to their online learning counterparts.

Web services have the potential to offer the enterprises with the ability to compose internal and external business services in order to accomplish complex processes. Service composition then becomes an increasingly challenging issue when complex and critical applications are built upon services with different QoS criteria. However, most of the existing QoS -aware compositions are simply based on the assumption that multiple criteria, no matter whether these multiple criteria are conflicting or not, can be combined into a single criterion to be optimized, according to some utility functions. In practice, this can be very difficult as utility functions or weights are not well known a priori. In this paper, a novel multi-objective approach is proposed to handle QoS -aware Web service composition with conflicting objectives and various restrictions on quality matrices. The proposed approach uses reinforcement learning to deal with the uncertainty characteristic inherent in open and decentralized environments. Experimental results reveal the ability of the proposed approach to find a set of Pareto optimal solutions, which have the equivalent quality to satisfy multiple QoS -objectives with different user preferences.