Exploiting heterogeneous scientific literature networks to combat ranking bias:evidence from the computational linguistics area

It is important to help researchers find valuable papers from a large literature collection. To this end, many graph-based ranking algorithms have been proposed. However, most of these algorithms suffer from the problem of ranking bias. Ranking bias hurts the usefulness of a ranking algorithm because it returns a ranking list with an undesirable time distribution. This paper is a focused study on how to alleviate ranking bias by leveraging the heterogeneous network structure of the literature collection. We propose a new graph-based ranking algorithm, MutualRank, that integrates mutual reinforcement relationships among networks of papers, researchers, and venues to achieve a more synthetic, accurate, and less-biased ranking than previous methods. MutualRank provides a unified model that involves both intra- and inter-network information for ranking papers, researchers, and venues simultaneously. We use the ACL Anthology Network as the benchmark data set and construct the gold standard from computer linguistics course websites of well-known universities and two well-known textbooks. The experimental results show that MutualRank greatly outperforms the state-of-the-art competitors, including PageRank, HITS, CoRank, Future Rank, and P-Rank, in ranking papers in both improving ranking effectiveness and alleviating ranking bias. Rankings of researchers and venues by MutualRank are also quite reasonable.

Benchmarking of distributed computing engines spark and GraphLab for big data analytics

In this paper we evaluate and compare two representativeand popular distributed processing engines for large scalebig data analytics, Spark and graph based engine GraphLab. Wedesign a benchmark suite including representative algorithmsand datasets to compare the performances of the computingengines, from performance aspects of running time, memory andCPU usage, network and I/O overhead. The benchmark suite istested on both local computer cluster and virtual machines oncloud. By varying the number of computers and memory weexamine the scalability of the computing engines with increasingcomputing resources (such as CPU and memory). We also runcross-evaluation of generic and graph based analytic algorithmsover graph processing and generic platforms to identify thepotential performance degradation if only one processing engineis available. It is observed that both computing engines showgood scalability with increase of computing resources. WhileGraphLab largely outperforms Spark for graph algorithms, ithas close running time performance as Spark for non-graphalgorithms. Additionally the running time with Spark for graphalgorithms over cloud virtual machines is observed to increaseby almost 100% compared to over local computer clusters.

Developing multidimensional metrics for evaluating paediatric neurodevelopmental disorders

Healthy brain functioning depends on efficient communication of information between brain regions, forming complex networks. By quantifying synchronisation between brain regions, a functionally connected brain network can be articulated. In neurodevelopmental disorders, where diagnosis is based on measures of behaviour and tasks, a measure of the underlying biological mechanisms holds promise as a potential clinical tool. Graph theory provides a tool for investigating the neural correlates of neuropsychiatric disorders, where there is disruption of efficient communication within and between brain networks. This research aimed to use recent conceptualisation of graph theory, along with measures of behaviour and cognitive functioning, to increase understanding of the neurobiological risk factors of atypical development. Using magnetoencephalography to investigate frequency-specific temporal dynamics at rest, the research aimed to identify potential biological markers derived from sensor-level whole-brain functional connectivity. Whilst graph theory has proved valuable for insight into network efficiency, its application is hampered by two limitations. First, its measures have hardly been validated in MEG studies, and second, graph measures have been shown to depend on methodological assumptions that restrict direct network comparisons. The first experimental study (Chapter 3) addressed the first limitation by examining the reproducibility of graph-based functional connectivity and network parameters in healthy adult volunteers. Subsequent chapters addressed the second limitation through adapted minimum spanning tree (a network analysis approach that allows for unbiased group comparisons) along with graph network tools that had been shown in Chapter 3 to be highly reproducible. Network topologies were modelled in healthy development (Chapter 4), and atypical neurodevelopment (Chapters 5 and 6). The results provided support to the proposition that measures of network organisation, derived from sensor-space MEG data, offer insights helping to unravel the biological basis of typical brain maturation and neurodevelopmental conditions, with the possibility of future clinical utility.

Next generation of recommender systems: Algorithms and applications

Personalized recommender systems aim to assist users in retrieving and accessing interesting items by automatically acquiring user preferences from the historical data and matching items with the preferences. In the last decade, recommendation services have gained great attention due to the problem of information overload. However, despite recent advances of personalization techniques, several critical issues in modern recommender systems have not been well studied. These issues include: (1) understanding the accessing patterns of users (i.e., how to effectively model users' accessing behaviors); (2) understanding the relations between users and other objects (i.e., how to comprehensively assess the complex correlations between users and entities in recommender systems); and (3) understanding the interest change of users (i.e., how to adaptively capture users' preference drift over time). To meet the needs of users in modern recommender systems, it is imperative to provide solutions to address the aforementioned issues and apply the solutions to real-world applications. ^ The major goal of this dissertation is to provide integrated recommendation approaches to tackle the challenges of the current generation of recommender systems. In particular, three user-oriented aspects of recommendation techniques were studied, including understanding accessing patterns, understanding complex relations and understanding temporal dynamics. To this end, we made three research contributions. First, we presented various personalized user profiling algorithms to capture click behaviors of users from both coarse- and fine-grained granularities; second, we proposed graph-based recommendation models to describe the complex correlations in a recommender system; third, we studied temporal recommendation approaches in order to capture the preference changes of users, by considering both long-term and short-term user profiles. In addition, a versatile recommendation framework was proposed, in which the proposed recommendation techniques were seamlessly integrated. Different evaluation criteria were implemented in this framework for evaluating recommendation techniques in real-world recommendation applications. ^ In summary, the frequent changes of user interests and item repository lead to a series of user-centric challenges that are not well addressed in the current generation of recommender systems. My work proposed reasonable solutions to these challenges and provided insights on how to address these challenges using a simple yet effective recommendation framework.^

Parallel Problem Solving from Nature – PPSN XIV:14th International Conference, Edinburgh, UK, September 17-21, 2016, Proceedings

This book constitutes the refereed proceedings of the 14th International Conference on Parallel Problem Solving from Nature, PPSN 2016, held in Edinburgh, UK, in September 2016. The total of 93 revised full papers were carefully reviewed and selected from 224 submissions. The meeting began with four workshops which offered an ideal opportunity to explore specific topics in intelligent transportation Workshop, landscape-aware heuristic search, natural computing in scheduling and timetabling, and advances in multi-modal optimization. PPSN XIV also included sixteen free tutorials to give us all the opportunity to learn about new aspects: gray box optimization in theory; theory of evolutionary computation; graph-based and cartesian genetic programming; theory of parallel evolutionary algorithms; promoting diversity in evolutionary optimization: why and how; evolutionary multi-objective optimization; intelligent systems for smart cities; advances on multi-modal optimization; evolutionary computation in cryptography; evolutionary robotics - a practical guide to experiment with real hardware; evolutionary algorithms and hyper-heuristics; a bridge between optimization over manifolds and evolutionary computation; implementing evolutionary algorithms in the cloud; the attainment function approach to performance evaluation in EMO; runtime analysis of evolutionary algorithms: basic introduction; meta-model assisted (evolutionary) optimization. The papers are organized in topical sections on adaption, self-adaption and parameter tuning; differential evolution and swarm intelligence; dynamic, uncertain and constrained environments; genetic programming; multi-objective, many-objective and multi-level optimization; parallel algorithms and hardware issues; real-word applications and modeling; theory; diversity and landscape analysis.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Hybrid Variable Neighborhood HyperHeuristics for Exam Timetabling Problems

This paper presents our work on analysing the high level search within a graph based hyperheuristic. The graph based hyperheuristic solves the problem at a higher level by searching through permutations of graph heuristics rather than the actual solutions. The heuristic permutations are then used to construct the solutions. Variable Neighborhood Search, Steepest Descent, Iterated Local Search and Tabu Search are compared. An analysis of their performance within the high level search space of heuristics is also carried out. Experimental results on benchmark exam timetabling problems demonstrate the simplicity and efficiency of this hyperheuristic approach. They also indicate that the choice of the high level search methodology is not crucial and the high level search should explore the heuristic search space as widely as possible within a limited searching time. This simple and general graph based hyperheuristic may be applied to a range of timetabling and optimisation problems.

Hybrid Variable Neighborhood HyperHeuristics for Exam Timetabling Problems

This paper presents our work on analysing the high level search within a graph based hyperheuristic. The graph based hyperheuristic solves the problem at a higher level by searching through permutations of graph heuristics rather than the actual solutions. The heuristic permutations are then used to construct the solutions. Variable Neighborhood Search, Steepest Descent, Iterated Local Search and Tabu Search are compared. An analysis of their performance within the high level search space of heuristics is also carried out. Experimental results on benchmark exam timetabling problems demonstrate the simplicity and efficiency of this hyperheuristic approach. They also indicate that the choice of the high level search methodology is not crucial and the high level search should explore the heuristic search space as widely as possible within a limited searching time. This simple and general graph based hyperheuristic may be applied to a range of timetabling and optimisation problems.

Production Diseases in European Organic Dairy Farms – Current Status and Identification of Drivers for Improvement by Means of a Systemic Approach

The aims of this thesis were to determine the animal health status in organic dairy farms in Europe and to identify drivers for improving the current situation by means of a systemic approach. Prevalences of production diseases were determined in 192 herds in Germany, France, Spain, and Sweden (Paper I), and stakeholder consultations were performed to investigate potential drivers to improve animal health on the sector level (ibid.). Interactions between farm variables were assessed through impact analysis and evaluated to identify general system behaviour and classify components according to their outgoing and incoming impacts (Paper II-III). The mean values and variances of prevalences indicate that the common rules of organic dairy farming in Europe do not result in consistently low levels of production diseases. Stakeholders deemed it necessary to improve the current status and were generally in favour of establishing thresholds for the prevalence of production diseases in organic dairy herds as well as taking actions to improve farms below that threshold. In order to close the gap between the organic principle of health and the organic farming practice, there is the need to formulate a common objective of good animal health and to install instruments to ensure and prove that the aim is followed by all dairy farmers in Europe who sell their products under the organic label. Regular monitoring and evaluation of herd health performance based on reference values are considered preconditions for identifying farms not reaching the target and thus in need of improvement. Graph-based impact analysis was shown to be a suitable method for modeling and evaluating the manifold interactions between farm factors and for identifying the most influential components on the farm level taking into account direct and indirect impacts as well as impact strengths. Variables likely to affect the system as a whole, and the prevalence of production diseases in particular, varied largely between farms despite some general tendencies. This finding reflects the diversity of farm systems and underlines the importance of applying systemic approaches in health management. Reducing the complexity of farm systems and indicating farm-specific drivers, i.e. areas in a farm, where changes will have a large impact, the presented approach has the potential to complement and enrich current advisory practice and to support farmers’ decision-making in terms of animal health.

A study of brain functional connectivity and cognitive processes in long COVID-19 patients

In this work, a prospective study conducted at the IRCCS Istituto delle Scienze Neurologiche di Bologna is presented. The aim was to investigate the brain functional connectivity of a cohort of patients (N=23) suffering from persistent olfactory dysfunction after SARS-CoV-2 infection (Post-COVID-19 syndrome), as compared to a matching group of healthy controls (N=26). In particular, starting from individual resting state functional-MRI data, different analytical approaches were adopted in order to find potential alterations in the connectivity patterns of patients’ brains. Analyses were conducted both at a whole-brain level and with a special focus on brain regions involved in the processing of olfactory stimuli (Olfactory Network). Statistical correlations between functional connectivity alterations and the results of olfactory and neuropsychological tests were investigated, to explore the associations with cognitive processes. The three approaches implemented for the analysis were the seed-based correlation analysis, the group-level Independent Component analysis and a graph-theoretical analysis of brain connectivity. Due to the relative novelty of such approaches, many implementation details and methodologies are not standardized yet and represent active research fields. Seed-based and group-ICA analyses’ results showed no statistically significant differences between groups, while relevant alterations emerged from those of the graph-based analysis. In particular, patients’ olfactory sub-graph appeared to have a less pronounced modular structure compared to the control group; locally, a hyper-connectivity of the right thalamus was observed in patients, with significant involvement of the right insula and hippocampus. Results of an exploratory correlation analysis showed a positive correlation between the graphs global modularity and the scores obtained in olfactory tests and negative correlations between the thalamus hyper-connectivity and memory tests scores.

An integer programming framework for sequencing cutting patterns based on interval graph completion

We derived a framework in integer programming, based on the properties of a linear ordering of the vertices in interval graphs, that acts as an edge completion model for obtaining interval graphs. This model can be applied to problems of sequencing cutting patterns, namely the minimization of open stacks problem (MOSP). By making small modifications in the objective function and using only some of the inequalities, the MOSP model is applied to another pattern sequencing problem that aims to minimize, not only the number of stacks, but also the order spread (the minimization of the stack occupation problem), and the model is tested.

Comparing Random-based and k-Anonymity-Based Algorithms for Graph Anonymization

Recently, several anonymization algorithms have appeared for privacy preservation on graphs. Some of them are based on random-ization techniques and on k-anonymity concepts. We can use both of them to obtain an anonymized graph with a given k-anonymity value. In this paper we compare algorithms based on both techniques in orderto obtain an anonymized graph with a desired k-anonymity value. We want to analyze the complexity of these methods to generate anonymized graphs and the quality of the resulting graphs.

Comparing Random-based and k-Anonymity-Based Algorithms for Graph Anonymization

Recently, several anonymization algorithms have appeared for privacy preservation on graphs. Some of them are based on random-ization techniques and on k-anonymity concepts. We can use both of them to obtain an anonymized graph with a given k-anonymity value. In this paper we compare algorithms based on both techniques in orderto obtain an anonymized graph with a desired k-anonymity value. We want to analyze the complexity of these methods to generate anonymized graphs and the quality of the resulting graphs.

An open source browser-based software tool for graph drawing and visualisation

In this research work we searched for open source libraries which supports graph drawing and visualisation and can run in a browser. Subsequent these libraries were evaluated to find out which one is the best for this task. The result was the d3.js is that library which has the greatest functionality, flexibility and customisability. Afterwards we developed an open source software tool where d3.js was included and which was written in JavaScript so that it can run browser-based.