Graph Processing Research Articles

The price of schedulability in cyclic workloads: The history-vs.-response-time-vs.-accuracy trade-off

Autonomous vehicles often employ computer-vision (CV) algorithms that track the movements of pedestrians and other vehicles to maintain safe distances from them. These algorithms are usually expressed as real-time processing graphs that have cycles due to back edges that provide history information. If immediate back history is required, then such a cycle must execute sequentially. Due to this requirement, any graph that contains a cycle with utilization exceeding 1.0 is categorically unschedulable, i.e., bounded graph response times cannot be guaranteed. Unfortunately, such cycles can occur in practice, particularly if conservative execution-time assumptions are made, as befits a safety-critical system. This dilemma can be obviated by allowing older back history, which enables parallelism in cycle execution at the expense of possibly affecting the accuracy of tracking. However, the efficacy of this solution hinges on the resulting history-vs.-response-time-vs.-accuracy trade-off that it exposes. In this paper, this trade-off is explored in depth through both a study of response-time bounds of synthetic task systems and an experimental study conducted using the open-source CARLA autonomous-driving simulator. Somewhat surprisingly, easing away from always requiring immediate back history proved to have only a marginal impact on accuracy, while greatly reducing analytical response-time bounds.

Optimal configuration and economic analysis of PRO-retrofitted industrial networks for sustainable energy production and material recovery considering uncertainties: Bioethanol and sugar mill case study

In this study, an optimal scheme is proposed by utilizing waste streams at a plant-wide scale along with pressure retarded osmosis (PRO) membrane allocation in complex industrial networks for energy recovery. Chemical exergy pinch analysis (ChExPA) and process graph (P-graph) are used to address the problem. The ultimate goals of utilizing the tools are (1) determine the optimal external load consumption, (2) minimizing the waste discharge, and (3) sustainable energy production while utilizing high chemical exergy potential waste discharges. A reliability assessment assisted with Monte-Carlo simulation is further performed to evaluate the proposed solutions from P-graph considering uncertainties. The effectiveness of the proposed methodology is explained using three industrial case studies which covered both intra-plant and inter-plant networks. The results indicated that ChExPA and P-graph can effectively identify the optimal location of the PRO membrane in industrial networks. Upon analyzing the complex inter-plant industrial networks 7.795 MW net power output was harnessed, and significantly higher waste of 384.92 kg/s was recovered with a levelized cost of energy of 0.073 $/kWh. The inter-plant network shows the greatest net profit which accounted for approximately $1,191,000 (i.e., 5.84 times higher than stand-alone plants) with a reasonable payback-period of 4.5 years.

A Study on Hybrid Hierarchical Network Representation Learning

Network representation learning (NRL) aims to convert nodes of a network into vector forms in Euclidean space. The information of a network is needed to be preserved as much as possible when NRL converts nodes into vector representation. A hybrid approach proposed in this paper is a framework to improve other NRL methods by considering the structure of densely connected nodes (community-like structure). HARP [1] is to contract a network into a series of contracted networks and embed them from the high-level contracted network to the low-level one. The vector representation (or embedding) for a high-level contracted network is used to initialize the learning process of a low-level contracted graph hierarchically. In this method (Hybrid Approach), HARP is revised by using a well-designed initialization process on the most high-level contracted network to preserve more community-like structure information.

Second Language Learners’ Pauses Over Different Times Intervals in L2 Writing Essays: Evidence From a Keystroke Logging Program

Purpose. Several studies have been conducted to analyse students’ pauses during first language and/or second language writing to indicate the magnitude of the underlying cognitive processes learners have. Majority of studies have examined students’ pauses at a threshold 200ms. However, little is known about recording second language learners' pauses at different pauses’ times over different types of genres. The current investigation reports a case study of L2 learners’ cognitive processes by recording their pauses (<500ms, <1000ms, and <2000ms) during L2 writing in response to multiple genres prompts. 
 Design / methodology / approach. Twenty-five postgraduate students were asked to write three essays over three weeks, and their writing processes were recorded using a keystroke logging program (Inputlog, 7, Leijten & van Waes, 2013). Data was triangulated using a log file from the keystroke logging program, a process graph for writing behavior through different stages, and a visual video recording of their captured screens during writing behaviours. 
 Findings. Results found that the students paused over sentence and paragraph boundaries and their pauses between paragraphs were significantly higher in writing narrative essay than in their argumentative essays at pauses intervals <500 and <1000ms respectively, and in turn, their pauses between sentences in an argumentative essay were significantly higher than their pauses in a descriptive essay at <500, <1000 respectively. However, there were no significant differences across word boundaries over genre types. 
 Conclusions. The current study extends the previous literature in examining the underlying cognitive processes during L2 writing tasks as the trendy issue of psycholinguistics. Knowing the cognitive processes is crucial in diagnosing the students’ difficulties in writing L2 essays as advanced technology has the potential to explore intrusively the accurate cognitive processes learners involved during writing tasks.
 Originality / value. This paper is innovative in examining a state-of-the-art issue and has implications to the field of psycholinguistics.

Synthesizing Brain-network-inspired Interconnections for Large-scale Network-on-chips

Brain network is a large-scale complex network with scale-free, small-world, and modularity properties, which largely supports this high-efficiency massive system. In this article, we propose to synthesize brain-network-inspired interconnections for large-scale network-on-chips. First, we propose a method to generate brain-network-inspired topologies with limited scale-free and power-law small-world properties, which have a low total link length and extremely low average hop count approximately proportional to the logarithm of the network size. In addition, given the large-scale applications, considering the modularity of the brain-network-inspired topologies, we present an application mapping method, including task mapping and deterministic deadlock-free routing, to minimize the power consumption and hop count. Finally, a cycle-accurate simulator BookSim2 is used to validate the architecture performance with different synthetic traffic patterns and large-scale test cases, including real-world communication networks for the graph processing application. Experiments show that, compared with other topologies and methods, the brain-network-inspired network-on-chips (NoCs) generated by the proposed method present significantly lower average hop count and lower average latency. Especially in graph processing applications with a power-law and tightly coupled inter-core communication, the brain-network-inspired NoC has up to 70% lower average hop count and 75% lower average latency than mesh-based NoCs.

Motion and Geometric Feature Analysis for Real-time Automatic Micro-expression Recognition Systems

The trend of real-time micro-expression recognition systems has increased with recent advancements in human-computer interaction (HCI) in security and healthcare. Several studies in this field contributed towards recognition accuracy, while few studies look into addressing the computation costs. In this paper, two approaches for micro-expression feature extraction are analyzed for real-time automatic micro-expression recognition. Firstly, motion-based approach, which calculates motion of subtle changes from an image sequence and present as features. Then, secondly, a low computational geometric-based feature extraction technique, a very popular method for facial expression recognition in real-time. These approaches were integrated in a developed system together with a facial landmark detection algorithm and a classifier for real-time analysis. Moreover, the recognition performance were evaluated using SMIC, CASME, CAS(ME)2 and SAMM datasets. The results suggest that the optimized Bi-WOOF (leveraging on motion-based features) yields the highest accuracy of 68.5%, while the full-face graph (leveraging on geometric-based features) yields 75.53% on the SAMM dataset. On the other hand, the optimized Bi-WOOF processes sample at 0.36 seconds and full-face graph processes sample at 0.10 seconds with a 640x480 image size. All experiments were performed on an Intel i5-3470 machine.

An efficient memory data organization strategy for application-characteristic graph processing

An efficient memory data organization strategy for application-characteristic graph processing

FDGLib: A Communication Library for Efficient Large-Scale Graph Processing in FPGA-Accelerated Data Centers

FDGLib: A Communication Library for Efficient Large-Scale Graph Processing in FPGA-Accelerated Data Centers

LargeGraph

Many out-of-GPU-memory systems are recently designed to support iterative processing of large-scale graphs. However, these systems still suffer from long time to converge because of inefficient propagation of active vertices’ new states along graph paths. To efficiently support out-of-GPU-memory graph processing, this work designs a system LargeGraph . Different from existing out-of-GPU-memory systems, LargeGraph proposes a dependency-aware data-driven execution approach , which can significantly accelerate active vertices’ state propagations along graph paths with low data access cost and also high parallelism. Specifically, according to the dependencies between the vertices, it only loads and processes the graph data associated with dependency chains originated from active vertices for smaller access cost. Because most active vertices frequently use a small evolving set of paths for their new states’ propagation because of power-law property, this small set of paths are dynamically identified and maintained and efficiently handled on the GPU to accelerate most propagations for faster convergence, whereas the remaining graph data are handled over the CPU. For out-of-GPU-memory graph processing, LargeGraph outperforms four cutting-edge systems: Totem (5.19–11.62×), Graphie (3.02–9.41×), Garaph (2.75–8.36×), and Subway (2.45–4.15×).

An overview of complex data stream ensemble classification

With the rapid development of information technology, data streams in various fields are showing the characteristics of rapid arrival, complex structure and timely processing. Complex types of data streams make the classification performance worse. However, ensemble classification has become one of the main methods of processing data streams. Ensemble classification performance is better than traditional single classifiers. This article introduces the ensemble classification algorithms of complex data streams for the first time. Then overview analyzes the advantages and disadvantages of these algorithms for steady-state, concept drift, imbalanced, multi-label and multi-instance data streams. At the same time, the application fields of data streams are also introduced which summarizes the ensemble algorithms processing text, graph and big data streams. Moreover, it comprehensively summarizes the verification technology, evaluation indicators and open source platforms of complex data streams mining algorithms. Finally, the challenges and future research directions of ensemble learning algorithms dealing with uncertain, multi-type, delayed, multi-type concept drift data streams are given.

An automatic machining process decision-making system based on knowledge graph

ABSTRACT Automatic process decision-making is a key module in intelligent process design(IPD), which determines the intelligence degree of IPD and affects the quality of product design. The traditional process decision-making method fails to solve the problem of knowledge expression, especially the integration of enterprise manufacturing resources and process knowledge. What’s more, heterogeneous knowledge also leads to the application of traditional knowledge mainly in keyword retrieval. So the process reasoning is mainly applied to the feature level, but the reasoning ability for the part level is weak. To overcome the above problems, the Knowledge Graph(KG) is introduced into the automatic machining process decision-making system. Firstly, a three-level information model is built to reorganize part information, process knowledge, and equipment resources based on KG. Secondly, the process reasoning framework based on KG is established, which is composed of process knowledge graph(PKG) information and process reasoning algorithm. Thirdly, to integrate process reasoning based on PKG, a hybrid reasoning algorithm based on semantic analysis(SA) and attributes weighting(AW) is built, which solved the problem of heterogeneity among process knowledge when making decisions. Finally, a prototype system was developed, and the aero-engine cone gear axis was tested to verify the effectiveness of the proposed system.

Social Cohesion: Mitigating Societal Risk in Case Studies of Digital Media in Hurricanes Harvey, Irma, and Maria.

Natural disasters affect thousands of communities every year, leaving behind human losses, billions of dollars in rebuilding efforts, and psychological affectation in survivors. How fast a community recovers from a disaster or even how well a community can mitigate risk from disasters depends on how resilient that community is. One main factor that influences communities' resilience is how a community comes together in times of need. Social cohesion is considered to be"the glue that holds society together, which can be better examined in a critical situation. There is no consensus on measuring social cohesion, but recent literature indicates that social media communications and communities play an essential role in today's disaster mitigation strategies.This research explores how to quantify social cohesion through social media outlets during disasters. The approach involves combining and implementing text processing techniques and graph network analysis to understand the relationships between nine different types of participants during hurricanes Harvey, Irma, and Maria. Visualizations are employed to illustrate these connections, their evolution before, during, and after disasters, and the degree of social cohesion throughout their timeline. The proposed measurement of social cohesion through social media networks presented in this work can provide future risk management and disaster mitigation policies. This social cohesion measure identifies the types of actors in a social network and how this network varies daily. Therefore, decisionmakers could use this measure to release strategic communication before, during, and after a disaster strikes, thus providing relevant information to people inneed.

Firefighting on the hexagonal grid

The firefighter problem with k firefighters on an infinite graph G is an iterative graph process, defined as follows: Suppose a fire breaks out at a given vertex v∈V(G) on Turn 1. On each subsequent even turn, k firefighters protect k vertices that are not on fire, and on each subsequent odd turn, any vertex that is on fire spreads the fire to all adjacent unprotected vertices. The firefighters’ goal is to eventually stop the spread of the fire. If there exists a strategy for k firefighters to eventually stop the spread of the fire, then we say G is k-containable.We consider the firefighter problem on the hexagonal grid, which is the graph whose vertices and edges are exactly the vertices and edges of a regular hexagonal tiling of the plane. It is not known if the hexagonal grid is 1-containable. In Gavenčiak et al. (2014), it was shown that if the firefighters have one firefighter per turn and one extra firefighter on two turns, the firefighters can contain the fire. We improve on this result by showing that even with only one extra firefighter on one turn, the firefighters can still contain the fire.

SortCache

Sparse data applications have irregular access patterns that stymie modern memory architectures. Although hyper-sparse workloads have received considerable attention in the past, moderately-sparse workloads prevalent in machine learning applications, graph processing and HPC have not. Where the former can bypass the cache hierarchy, the latter fit in the cache. This article makes the observation that intelligent, near-processor cache management can improve bandwidth utilization for data-irregular accesses, thereby accelerating moderately-sparse workloads. We propose SortCache, a processor-centric approach to accelerating sparse workloads by introducing accelerators that leverage the on-chip cache subsystem, with minimal programmer intervention.

Hamilton cycles in the semi-random graph process

The semi-random graph process is a single player game in which the player is initially presented an empty graph on n vertices. In each round, a vertex u is presented to the player independently and uniformly at random. The player then adaptively selects a vertex v, and adds the edge uv to the graph. For a fixed monotone graph property, the objective of the player is to force the graph to satisfy this property with high probability in as few rounds as possible.We focus on the problem of constructing a Hamilton cycle in as few rounds as possible. In particular, we present a novel strategy for the player which achieves a Hamiltonian cycle in c∗n rounds, where the value of c∗ is the result of a high dimensional optimization problem. Numerical computations indicate that c∗<2.61135. This improves upon the previously best known upper bound of 3n rounds. We also show that the previously best lower bound of (ln2+ln(1+ln2)+o(1))n is not tight.

Parallel Business Processes Modeling

The article considers a new section of the modern theory of business processes dedicated to their parallel processing. The relevance of the work is due to the need to reorganize business processes in order to improve a number of their key indicators, such as speed, cost, etc. It should be noted that the well-known models and methods of the modern theory of business processes practically do not address the issues of parallelism in them, although this direction occupies a significant place in the general theory of processes and, in addition to the actual methods of description, analysis and verification of parallel structures, also includes methods of parallelization of sequential structures. The paper proposes a classification of parallel business processes based on the types of parallel computing systems and completely covering the subject area under consideration. Examples of parallel business processes of each type are given. For each of the selected classes of business processes, a brief overview of the current state of affairs in terms of parallelism is given; the directions of relevant work are identified and analyzed. Brief descriptions of models and methods of pipelined and synchronous parallelism are given. In terms of asynchronous parallelism, a model and language tools for organizing parallel independent branches (processes) are proposed. A mixed graph containing nodes and branches of various types is used as the corresponding model. The scenario of executing a parallel business process is formalized. To estimate the execution time of a parallel business process, the basic theorems of the theory of computational processes are adapted in order to focus them on business processes, recommendations are given on the rules for building parallel business processes. The requirements for the language tools for describing asynchronous parallel business processes are formulated. Next, the methods of parallelization of business processes related to its linear sections and cycles are considered. The definitions of the linear section and the cycle in the business process are introduced. For their parallelization, the key task is to identify information dependencies between the functions of the business process. Attention is drawn to the sequence of definitions/uses of information objects, manifested through incoming and outgoing information flows for functional objects of the corresponding visual modeling language. In terms of the above-mentioned business process graph, the concepts of information dependence of various types are formalized. The proposed work is one of the first attempts to build a formal basis for the organization of parallelism in business processes, which plays an important role in improving the key indicators of business processes in the tasks of their reorganization.

The future is big graphs

Ensuring the success of big graph processing for the next decade and beyond.

Grafs: declarative graph analytics

Graph analytics elicits insights from large graphs to inform critical decisions for business, safety and security. Several large-scale graph processing frameworks feature efficient runtime systems; however, they often provide programming models that are low-level and subtly different from each other. Therefore, end users can find implementation and specially optimization of graph analytics error-prone and time-consuming. This paper regards the abstract interface of the graph processing frameworks as the instruction set for graph analytics, and presents Grafs, a high-level declarative specification language for graph analytics and a synthesizer that automatically generates efficient code for five high-performance graph processing frameworks. It features novel semantics-preserving fusion transformations that optimize the specifications and reduce them to three primitives: reduction over paths, mapping over vertices and reduction over vertices. Reductions over paths are commonly calculated based on push or pull models that iteratively apply kernel functions at the vertices. This paper presents conditions, parametric in terms of the kernel functions, for the correctness and termination of the iterative models, and uses these conditions as specifications to automatically synthesize the kernel functions. Experimental results show that the generated code matches or outperforms handwritten code, and that fusion accelerates execution.

Multi-source information fusion based on factor graph in autonomous underwater vehicles navigation systems

PurposeThis paper aims to present a multi-source information fusion algorithm based on factor graph for autonomous underwater vehicles (AUVs) navigation and positioning to address the asynchronous and heterogeneous problem of multiple sensors.Design/methodology/approachThe factor graph is formulated by joint probability distribution function (pdf) random variables. All available measurements are processed into an optimal navigation solution by the message passing algorithm in the factor graph model. To further aid high-rate navigation solutions, the equivalent inertial measurement unit (IMU) factor is introduced to replace several consecutive IMU measurements in the factor graph model.FindingsThe proposed factor graph was demonstrated both in a simulated and vehicle environment using IMU, Doppler Velocity Log, terrain-aided navigation, magnetic compass pilot and depth meter sensors. Simulation results showed that the proposed factor graph processes all available measurements into the considerably improved navigation performance, computational efficiency and complexity compared with the un-simplified factor graph and the federal Kalman filtering methods. Semi-physical experiment results also verified the robustness and effectiveness.Originality/valueThe proposed factor graph scheme supported a plug and play capability to easily fuse asynchronous heterogeneous measurements information in AUV navigation systems.

Predicting User Activity Intensity Using Geographic Interactions Based on Social Media Check-In Data

Predicting user activity intensity is crucial for various applications. However, existing studies have two main problems. First, as user activity intensity is nonstationary and nonlinear, traditional methods can hardly fit the nonlinear spatio-temporal relationships that characterize user mobility. Second, user movements between different areas are valuable, but have not been utilized for the construction of spatial relationships. Therefore, we propose a deep learning model, the geographical interactions-weighted graph convolutional network-gated recurrent unit (GGCN-GRU), which is good at fitting nonlinear spatio-temporal relationships and incorporates users’ geographic interactions to construct spatial relationships in the form of graphs as the input. The model consists of a graph convolutional network (GCN) and a gated recurrent unit (GRU). The GCN, which is efficient at processing graphs, extracts spatial features. These features are then input into the GRU, which extracts their temporal features. Finally, the GRU output is passed through a fully connected layer to obtain the predictions. We validated this model using a social media check-in dataset and found that the geographical interactions graph construction method performs better than the baselines. This indicates that our model is appropriate for fitting the complex nonlinear spatio-temporal relationships that characterize user mobility and helps improve prediction accuracy when considering geographic flows.