Code Search is a practical tool that helps developers navigate growing source code repositories by connecting natural language queries with code snippets. Platforms such as StackOverflow resolve coding questions and answers; however, they cannot perform a semantic search through the code. Moreover, poorly documented code adds more complexity to search for code snippets in repositories. To tackle this challenge, this paper presents Siambert, a BERT-based model that gets the question in natural language and returns relevant code snippets. The Siambert architecture consists of two stages, where the first stage, inspired by Siamese Neural Network, returns the top K relevant code snippets to the input questions, and the second stage ranks the given snippets by the first stage. The experiments show that Siambert outperforms non-BERT-based models having improvements that range from 12% to 39% on the Recall@1 metric and improves the inference time performance, making it 15x faster than standard BERT models

In the era of big data, considerable research focus is being put on designing efficient algorithms capable of learning and extracting high-level knowledge from ubiquitous data streams in an online fashion. While, most existing algorithms assume that data samples are drawn from a stationary distribution, several complex environments deal with data streams that are subject to change over time. Taking this aspect into consideration is an important step towards building truly aware and intelligent systems. In this paper, we propose GNG-A, an adaptive method for incremental unsupervised learning from evolving data streams experiencing various types of change. The proposed method maintains a continuously updated network (graph) of neurons by extending the Growing Neural Gas algorithm with three complementary mechanisms, allowing it to closely track both gradual and sudden changes in the data distribution. First, an adaptation mechanism handles local changes where the distribution is only non-stationary in some regions of the feature space. Second, an adaptive forgetting mechanism identifies and removes neurons that become irrelevant due to the evolving nature of the stream. Finally, a probabilistic evolution mechanism creates new neurons when there is a need to represent data in new regions of the feature space. The proposed method is demonstrated for anomaly and novelty detection in non-stationary environments. Results show that the method handles different data distributions and efficiently reacts to various types of change. 

Balanced graph partitioning is an NP-complete problem with a wide range of applications. These applications include many large-scale distributed problems, including the optimal storage of large sets of graph-structured data over several hosts. However, in very large-scale distributed scenarios, state-of-the-art algorithms are not directly applicable because they typically involve frequent global operations over the entire graph. In this article, we propose a fully distributed algorithm called Ja-be-Ja that uses local search and simulated annealing techniques for two types of graph partitioning: edge-cut partitioning and vertex-cut partitioning. The algorithm is massively parallel: There is no central coordination, each vertex is processed independently, and only the direct neighbors of a vertex and a small subset of random vertices in the graph need to be known locally. Strict synchronization is not required. These features allow Ja-be-Ja to be easily adapted to any distributed graph-processing system from data centers to fully distributed networks. We show that the minimal edge-cut value empirically achieved by Ja-be-Ja is comparable to state-of-the-art centralized algorithms such as Metis. In particular, on large social networks, Ja-be-Ja outperforms Metis. We also show that Ja-be-Ja computes very low vertex-cuts, which are proved significantly more effective than edge-cuts for processing most real-world graphs.

Graph processing has become an integral part of big data analytics. With the ever increasing size of the graphs, one needs to partition them into smaller clusters, which can be managed and processed more easily on multiple machines in a distributed fashion. While there exist numerous solutions for edge-cut partitioning of graphs, very little effort has been made for vertex-cut partitioning. This is in spite of the fact that vertex-cuts are proved significantly more effective than edge-cuts for processing most real world graphs. In this paper we present Ja-be-Ja-vc, a parallel and distributed algorithm for vertex-cut partitioning of large graphs. In a nutshell, Ja-be-Ja-vc is a local search algorithm that iteratively improves upon an initial random assignment of edges to partitions. We propose several heuristics for this optimization and study their impact on the final partitioning. Moreover, we employ simulated annealing technique to escape local optima. We evaluate our solution on various graphs and with variety of settings, and compare it against two state-of-the-art solutions. We show that Ja-be-Ja-vc outperforms the existing solutions in that it not only creates partitions of any requested size, but also requires a vertex-cut that is better than its counterparts and more than 70% better than random partitioning.

Balanced graph partitioning is a well known NP-complete problem with a wide range of applications. These applications include many large-scale distributed problems such as the optimal storage of large sets of graph-structured data over several hosts, or identifying clusters in on-line social networks. In such very large-scale distributed scenarios, state-of-the-art algorithms are not directly applicable, because they typically involve frequent global operations over the entire graph. In this paper, we propose a distributed graph partitioning algorithm, called Ja-be-Ja1. The algorithm is massively parallel: each graph node is processed independently, and only the direct neighbors of the node, and a small subset of random nodes in the graph need to be known. Strict synchronization is not required. These features allow Ja-be-Ja to be easily adapted to any distributed graph-processing system from data centers to fully distributed networks. We perform a thorough experimental analysis, which shows that the minimal edge-cut value achieved by Ja-be-Ja is comparable to state-of-the-art centralized algorithms such as Metis. In particular, on large social networks Ja-be-Ja outperforms Metis.

Monitoring the global state of an overlay network is vital for the self-management of peer-to-peer (P2P) systems. Gossip-based algorithms are a well-known technique that can provide nodes locally with aggregated knowledge about the state of the overlay network. In this paper, we present a gossip-based protocol to estimate the global distribution of attribute values stored across a set of nodes in the system. Our algorithm estimates the distribution both efficiently and accurately. The key contribution of our algorithm is that it has substantially lower overhead than existing distribution estimation algorithms. We evaluated our system in simulation, and compared it against the state-of-the-art solutions. The results show similar accuracy to its counterparts, but with a communication overhead of an order of magnitude lower than them.

Peer-to-Peer (P2P) live media streaming is an emerging technology that reduces the barrier to stream live events over the Internet. However, providing a high quality media stream using P2P overlay networks is challenging and gives raise to a number of issues: (i) how to guarantee quality of the service (QoS) in the presence of dynamism, (ii) how to incentivize nodes to participate in media distribution, (iii) how to avoid bottlenecks in the overlay, and (iv) how to deal with nodes that reside behind Network Address Translators gateways (NATs). In this thesis, we answer the above research questions in form of new algorithms and systems. First of all, we address problems (i) and (ii) by presenting our P2P live media streaming solutions: Sepidar, which is a multiple-tree overlay, and GLive, which is a mesh overlay. In both models, nodes with higher upload bandwidth are positioned closer to the media source. This structure reduces the playback latency and increases the playback continuity at nodes, and also incentivizes the nodes to provide more upload bandwidth. We use a reputation model to improve participating nodes in media distribution in Sepidar and GLive. In both systems, nodes audit the behaviour of their directly connected nodes by getting feedback from other nodes. Nodes who upload more of the stream get a relatively higher reputation, and proportionally higher quality streams. To construct our streaming overlay, we present a distributed market model inspired by Bertsekas auction algorithm, although our model does not rely on a central server with global knowledge. In our model, each node has only partial information about the system. Nodes acquire knowledge of the system by sampling nodes using the Gradient overlay, where it facilitates the discovery of nodes with similar upload bandwidth. We address the bottlenecks problem, problem (iii), by presenting CLive that satisfies real-time constraints on delay between the generation of the stream and its actual delivery to users. We resolve this problem by borrowing some resources (helpers) from the cloud, upon need. In our approach, helpers are added on demand to the overlay, to increase the amount of total available bandwidth, thus increasing the probability of receiving the video on time. As the use of cloud resources costs money, we model the problem as the minimization of the economical cost, provided that a set of constraints on QoS is satisfied. Finally, we solve the NAT problem, problem (iv), by presenting two NAT-aware peer sampling services (PSS): Gozar and Croupier. Traditional gossip-based PSS breaks down, where a high percentage of nodes are behind NATs. We overcome this problem in Gozar using one-hop relaying to communicate with the nodes behind NATs. Croupier similarly implements a gossip-based PSS, but without the use of relaying.

Community networking is an emerging model of a shared communication infrastructure in which communities of citizens build and own open networks. Community networks offer successfully IP-based networking to the user. Cloud computing infrastructures however, while common in today's Internet, hardy exist in community networks. We explain our approach to bring clouds into the Guifi.net community network. For this we have started integrating part of our cloud prototype into the Guifi.net community network management tools. A proof-of-concept cloud infrastructure is currently under deployment in the Guifi.net community network. Our long term vision is that the users of community networks will not need to consume cloud applications from the Internet, but find them within the community network.

Peer-to-peer (P2P) video streaming is an emerging technology that reduces the barrier to stream live events over the Internet. Unfortunately, satisfying soft real-time constraints on the delay between the generation of the stream and its actual delivery to users is still a challenging problem. Bottlenecks in the available upload bandwidth, both at the media source and inside the overlay network, may limit the quality of service (QoS) experienced by users. A potential solution for this problem is assisting the P2P streaming network by a cloud computing infrastructure to guarantee a minimum level of QoS. In such approach, rented cloud resources (helpers) are added on demand to the overlay, to increase the amount of total available bandwidth and the probability of receiving the video on time. Hence, the problem to be solved becomes minimizing the economical cost, provided that a set of constraints on QoS is satisfied. The main contribution of this paper is CLIVE, a cloud-assisted P2P live streaming system that demonstrates the feasibility of these ideas. CLIVE estimates the available capacity in the system through a gossip-based aggregation protocol and provisions the required resources from the cloud to guarantee a given level of QoS at low cost. We perform extensive simulations and evaluate CLIVE using large-scale experiments under dynamic realistic settings.