| 1. |
- Abbas, Zainab, 1991-, et al.
(author)
-
Short-Term Traffic Prediction Using Long Short-Term Memory Neural Networks
- 2018
-
In: Proceedings - 2018 IEEE International Congress on Big Data, BigData Congress 2018 - Part of the 2018 IEEE World Congress on Services. - : Institute of Electrical and Electronics Engineers Inc.. - 9781538672327 ; , s. 57-65
-
Conference paper (peer-reviewed)abstract
- Short-term traffic prediction allows Intelligent Transport Systems to proactively respond to events before they happen. With the rapid increase in the amount, quality, and detail of traffic data, new techniques are required that can exploit the information in the data in order to provide better results while being able to scale and cope with increasing amounts of data and growing cities. We propose and compare three models for short-term road traffic density prediction based on Long Short-Term Memory (LSTM) neural networks. We have trained the models using real traffic data collected by Motorway Control System in Stockholm that monitors highways and collects flow and speed data per lane every minute from radar sensors. In order to deal with the challenge of scale and to improve prediction accuracy, we propose to partition the road network into road stretches and junctions, and to model each of the partitions with one or more LSTM neural networks. Our evaluation results show that partitioning of roads improves the prediction accuracy by reducing the root mean square error by the factor of 5. We show that we can reduce the complexity of LSTM network by limiting the number of input sensors, on average to 35% of the original number, without compromising the prediction accuracy. .
|
|
| 2. |
- Aberer, Karl, et al.
(author)
-
The Essence of P2P : A Reference Architecture for Overlay Networks
- 2005
-
In: Fifth IEEE International Conference on Peer-to-Peer Computing, Proceedings. - 0769523765 ; , s. 11-20
-
Conference paper (peer-reviewed)abstract
- The success of the P2P idea has created a huge diversity of approaches, among which overlay networks, for example, Gnutella, Kazaa, Chord, Pastry, Tapestry, P-Grid, or DKS, have received specific attention from both developers and researchers. A wide variety of algorithms, data structures, and architectures have been proposed. The terminologies and abstractions used, however have become quite inconsistent since the P2P paradigm has attracted people from many different communities, e.g., networking, databases, distributed systems, graph theory, complexity theory, biology, etc. In this paper we propose a reference model for overlay networks which is capable of modeling different approaches in this domain in a generic manner It is intended to allow researchers and users to assess the properties of concrete systems, to establish a common vocabulary for scientific discussion, to facilitate the qualitative comparison of the systems, and to serve as the basis for defining a standardized API to make overlay networks interoperable.
|
|
| 3. |
- Alkathiri, Abdul Aziz, et al.
(author)
-
Decentralized Word2Vec Using Gossip Learning
- 2021
-
In: Proceedings of the 23<sup>rd</sup> Nordic Conference on Computational Linguistics (NoDaLiDa 2021).
-
Conference paper (peer-reviewed)abstract
- Advanced NLP models require huge amounts of data from various domains to produce high-quality representations. It is useful then for a few large public and private organizations to join their corpora during training. However, factors such as legislation and user emphasis on data privacy may prevent centralized orchestration and data sharing among these organizations. Therefore, for this specific scenario, we investigate how gossip learning, a massively-parallel, data-private, decentralized protocol, compares to a shared-dataset solution. We find that the application of Word2Vec in a gossip learning framework is viable. Without any tuning, the results are comparable to a traditional centralized setting, with a reduction in ground-truth similarity scores as low as 4.3%. Furthermore, the results are up to 54.8% better than independent local training.
|
|
| 4. |
- Antaris, Stefanos, 1988-, et al.
(author)
-
A Deep Graph Reinforcement Learning Model for Improving User Experience in Live Video Streaming
- 2021
-
In: 2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1787-1796
-
Conference paper (peer-reviewed)abstract
- In this paper we present a deep graph reinforcement learning model to predict and improve the user experience during a live video streaming event, orchestrated by an agent/tracker. We first formulate the user experience prediction problem as a classification task, accounting for the fact that most of the viewers at the beginning of an event have poor quality of experience due to low-bandwidth connections and limited interactions with the tracker. In our model we consider different factors that influence the quality of user experience and train the proposed model on diverse state-action transitions when viewers interact with the tracker. In addition, provided that past events have various user experience characteristics we follow a gradient boosting strategy to compute a global model that learns from different events. Our experiments with three real-world datasets of live video streaming events demonstrate the superiority of the proposed model against several baseline strategies. Moreover, as the majority of the viewers at the beginning of an event has poor experience, we show that our model can significantly increase the number of viewers with high quality experience by at least 75% over the first streaming minutes. Our evaluation datasets and implementation are publicly available at https://publicresearch.z13.web.core.windows.net
|
|
| 5. |
- Antaris, Stefanos, 1988-, et al.
(author)
-
EGAD : Evolving Graph Representation Learning with Self-Attention and Knowledge Distillation for Live Video Streaming Events
- 2020
-
In: 2020 IEEE international conference on big data (big data). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1455-1464
-
Conference paper (peer-reviewed)abstract
- In this study, we present a dynamic graph representation learning model on weighted graphs to accurately predict the network capacity of connections between viewers in a live video streaming event. We propose EGAD, a neural network architecture to capture the graph evolution by introducing a self-attention mechanism on the weights between consecutive graph convolutional networks. In addition, we account for the fact that neural architectures require a huge amount of parameters to train, thus increasing the online inference latency and negatively influencing the user experience in a live video streaming event. To address the problem of the high online inference of a vast number of parameters, we propose a knowledge distillation strategy. In particular, we design a distillation loss function, aiming to first pretrain a teacher model on offline data, and then transfer the knowledge from the teacher to a smaller student model with less parameters. We evaluate our proposed model on the link prediction task on three real-world datasets, generated by live video streaming events. The events lasted 80 minutes and each viewer exploited the distribution solution provided by the company Hive Streaming AB. The experiments demonstrate the effectiveness of the proposed model in terms of link prediction accuracy and number of required parameters, when evaluated against state-of-the-art approaches. In addition, we study the distillation performance of the proposed model in terms of compression ratio for different distillation strategies, where we show that the proposed model can achieve a compression ratio up to 15:100, preserving high link prediction accuracy. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://stefanosantaris.github.io/EGAD.
|
|
| 6. |
- Antaris, Stefanos, 1988-
(author)
-
Enabling Enterprise Live Video Streaming with Reinforcement Learning and Graph Neural Networks
- 2022
-
Doctoral thesis (other academic/artistic)abstract
- Over the last decade, video has vastly become the most popular way the world consumes content. Due to the increased popularity, video has been a strategic tool for enterprises. More specifically, enterprises organize live video streaming events for both internal and external purposes in order to attract large audiences and disseminate important information. However, streaming a high- quality video internally in large multinational corporations, with thousands of employees spread around the world, is a challenging task. The main challenge is to prevent catastrophic network congestion in the enterprise network when thousand of employees attend a high-quality video event simultaneously. Given that large enterprises invest a significant amount of their annual budget on live video streaming events, it is essential to ensure that the office network will not be congested and each viewer will have high quality of experience during the event.To address this challenge, large enterprises employ distributed live video streaming solutions to distribute high-quality video content between viewers of the same network. Such solutions rely on prior knowledge of the enterprise network topology to efficiently reduce the network bandwidth requirements during the event. Given that such knowledge is not always feasible to acquire, the distributed solutions must detect the network topology in real-time during the event. However, distributed solutions require a service to detect the network topology in the first minutes of the event, also known as the joining phase. Failing to promptly detect the enterprise network topology negatively impacts the event’s performance. In particular, distributed solutions may establish connections between viewers of different offices with limited network capacity. As a result, the enterprise network will be congested, and the employees will drop the event from the beginning of the event if they experience video quality issues.In this thesis, we investigate and propose novel machine learning models allowing the enterprise network topology service to detect the topology in real- time. In particular, we investigate the network distribution of live video streaming events caused by the distributed software solutions. In doing so, we propose several graph neural network models to detect the network topology in the first minutes of the event. Live video streaming solutions can adjust the viewers’ connections to distribute high-quality video content between viewers of the same office, avoiding the risk of network congestion. We compare our models with several baselines in real-world datasets and show that our models achieve significant improvement via empirical evaluations.Another critical factor for the efficiency of live video streaming events is the enterprise network topology service latency. Distributed live video streaming solutions require minimum latency to infer the network topology and adjust the viewers’ connections. We study the impact of the graph neural network size on the model’s online inference latency and propose several knowledge distillation strategies to generate compact models. Therefore, we create models with significantly fewer parameters, reducing the online inference latency while achieving high accuracy in the network topology detection task. Compared with state-of-the-art approaches, our proposed models have several orders of magnitude fewer parameters while maintaining high accuracy.Furthermore, we address the continuously evolving enterprise network topology problem. Modern enterprise networks frequently change their topology to manage their business needs. Therefore, distributed live video streaming solutions must capture the network topology changes and adjust their network topology detection service in real time. To tackle this problem, we propose several novel machine learning models that exploit historical events to assist the models in detecting the network topology in the first minutes of the event. We investigate the distribution of the viewers participating in the events. We propose efficient reinforcement learning and meta-learning techniques to learn the enterprise network topology for each new event. By applying meta-learning and reinforcement learning, we can generalize network topology changes and ensure that every viewer will have a high-quality experience during an event. Compared with baseline approaches, we achieved superior performance in establishing connections between viewers of the same office in the first minutes of the event. Therefore, we ensure that distributed solutions provide a high return on investment in every live video streaming event without risking any enterprise network congestion.
|
|
| 7. |
- Antaris, Stefanos, 1988-, et al.
(author)
-
Knowledge distillation on neural networks for evolving graphs
- 2021
-
In: Social Network Analysis and Mining. - : SPRINGER WIEN. - 1869-5450 .- 1869-5469. ; 11:1
-
Journal article (peer-reviewed)abstract
- Graph representation learning on dynamic graphs has become an important task on several real-world applications, such as recommender systems, email spam detection, and so on. To efficiently capture the evolution of a graph, representation learning approaches employ deep neural networks, with large amount of parameters to train. Due to the large model size, such approaches have high online inference latency. As a consequence, such models are challenging to deploy to an industrial setting with vast number of users/nodes. In this study, we propose DynGKD, a distillation strategy to transfer the knowledge from a large teacher model to a small student model with low inference latency, while achieving high prediction accuracy. We first study different distillation loss functions to separately train the student model with various types of information from the teacher model. In addition, we propose a hybrid distillation strategy for evolving graph representation learning to combine the teacher's different types of information. Our experiments with five publicly available datasets demonstrate the superiority of our proposed model against several baselines, with average relative drop 40.60% in terms of RMSE in the link prediction task. Moreover, our DynGKD model achieves a compression ratio of 21: 100, accelerating the inference latency with a speed up factor x30, when compared with the teacher model. For reproduction purposes, we make our datasets and implementation publicly available at https://github.com/stefanosantaris/DynGKD.
|
|
| 8. |
- Antaris, Stefanos, et al.
(author)
-
Meta-reinforcement learning via buffering graph signatures for live video streaming events
- 2021
-
In: Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021. - New York, NY, USA : Association for Computing Machinery (ACM). ; , s. 385-392
-
Conference paper (peer-reviewed)abstract
- In this study, we present a meta-learning model to adapt the predictions of the network's capacity between viewers who participate in a live video streaming event. We propose the MELANIE model, where an event is formulated as a Markov Decision Process, performing meta-learning on reinforcement learning tasks. By considering a new event as a task, we design an actor-critic learning scheme to compute the optimal policy on estimating the viewers' high-bandwidth connections. To ensure fast adaptation to new connections or changes among viewers during an event, we implement a prioritized replay memory buffer based on the Kullback-Leibler divergence of the reward/throughput of the viewers' connections. Moreover, we adopt a model-agnostic meta-learning framework to generate a global model from past events. As viewers scarcely participate in several events, the challenge resides on how to account for the low structural similarity of different events. To combat this issue, we design a graph signature buffer to calculate the structural similarities of several streaming events and adjust the training of the global model accordingly. We evaluate the proposed model on the link weight prediction task on three real-world datasets of live video streaming events. Our experiments demonstrate the effectiveness of our proposed model, with an average relative gain of 25% against state-of-the-art strategies. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://github.com/stefanosantaris/melanie
|
|
| 9. |
- Apolonia, Nuno, et al.
(author)
-
Gossip-based service monitoring platform for wireless edge cloud computing
- 2017
-
In: Proceedings IEEE 14th International Conference on Networking, Sensing and Control (ICNSC). - : Institute of Electrical and Electronics Engineers (IEEE).
-
Conference paper (peer-reviewed)abstract
- Edge cloud computing proposes to support shared services, by using the infrastructure at the network's edge. An important problem is the monitoring and management of services across the edge environment. Therefore, dissemination and gathering of data is not straightforward, differing from the classic cloud infrastructure. In this paper, we consider the environment of community networks for edge cloud computing, in which the monitoring of cloud services is required. We propose a monitoring platform to collect near real-time data about the services offered in the community network using a gossip-enabled network. We analyze and apply this gossip-enabled network to perform service discovery and information sharing, enabling data dissemination among the community. We implemented our solution as a prototype and used it for collecting service monitoring data from the real operational community network cloud, as a feasible deployment of our solution. By means of emulation and simulation we analyze in different scenarios, the behavior of the gossip overlay solution, and obtain average results regarding information propagation and consistency needs, i.e. in high latency situations, data convergence occurs within minutes.
|
|
| 10. |
- Apolonia, Nuno, 1984-
(author)
-
On Service Optimization in Community Network Micro-Clouds
- 2018
-
Doctoral thesis (other academic/artistic)abstract
- Internet coverage in the world is still weak and local communities are required to come together and build their own network infrastructures. People collaborate for the common goal of accessing the Internet and cloud services by building Community networks (CNs).The use of Internet cloud services has grown over the last decade. Community network cloud infrastructures (i.e. micro-clouds) have been introduced to run services inside the network, without the need to consume them from the Internet. CN micro-clouds aims for not only an improved service performance, but also an entry point for an alternative to Internet cloud services in CNs. However, the adaptation of the services to be used in CN micro-clouds have their own challenges since the use of low-capacity devices and wireless connections without a central management is predominant in CNs. Further, large and irregular topology of the network, high software and hardware diversity and different service requirements in CNs, makes the CN micro-clouds a challenging environment to run local services, and to achieve service performance and quality similar to Internet cloud services. In this thesis, our main objective is the optimization of services (performance, quality) in CN micro-clouds, facilitating entrance to other services and motivating members to make use of CN micro-cloud services as an alternative to Internet services. We present an approach to handle services in CN micro-cloud environments in order to improve service performance and quality that can be approximated to Internet services, while also giving to the community motivation to use CN micro-cloud services. Furthermore, we break the problem into different levels (resource, service and middleware), propose a model that provides improvements for each level and contribute with information that helps to support the improvements (in terms of service performance and quality) in the other levels.At the resource level, we facilitate the use of community devices by utilizing virtualization techniques that isolate and manage CN micro-cloud services in order to have a multi-purpose environment that fosters services in the CN micro-cloud environment.At the service level, we build a monitoring tool tailored for CN micro-clouds that helps us to analyze service behavior and performance in CN micro-clouds. Subsequently, the information gathered enables adaptation of the services to the environment in order to improve their quality and performance under CN environments. At the middleware level, we build overlay networks as the main communication system according to the social information in order to improve paths and routes of the nodes, and improve transmission of data across the network by utilizing the relationships already established in the social network or community of practices that are related to the CNs. Therefore, service performance in CN micro-clouds can become more stable with respect to resource usage, performance and user perceived quality.
|
|
