The IDF (Inverse Document Frequency) term weighting method is a classic treatment of a term’s significance in information retrieval and text analytics. IDF can be derived from the information-theoretic Kullback-Leibler (KL) Divergence and has given rise to competitive methods such as TF*IDF and Okapi BM25, which is the default scoring function of ElasticSearch. We developed a new information metric called DLITE and derived from it an alternative to IDF, namely iDL, for term weighting and scoring in ranked information retrieval. In a series of experiments we conducted on multiple benchmark Text REtrieval Conference (TREC) collections, iDL methods consistently outperformed BM25, a very competitive baseline, for ad hoc retrieval. We outline the theoretical properties of DLITE that support the effectiveness of iDL. As a general information measure, we expect DLITE to be applicable in many other areas of big-data analytics and machine learning where further research will be valuable.

In recent years, cancer patients survival prediction holds important significance for worldwide health problems, and has gained many researchers attention in medical information communities. Cancer patients survival prediction can be seen the classification work which is a meaningful and challenging task. Nevertheless, research in this field is still limited. In this work, we design a novel Multimodal Graph Neural Network (MGNN)framework for predicting cancer survival, which explores the features of real-world multimodal data such as gene expression, copy number alteration and clinical data in a unified framework. Specifically, we first construct the bipartite graphs between patients and multimodal data to explore the inherent relation. Subsequently, the embedding of each patient on different bipartite graphs is obtained with graph neural network. Finally, a multimodal fusion neural layer is proposed to fuse the medical features from different modality data. Comprehensive experiments have been conducted on real-world datasets, which demonstrate the superiority of our modal with significant improvements against state-of-the-arts. Furthermore, the proposed MGNN is validated to be more robust on other four cancer datasets.

Predicting the survival of cancer patients holds significant meaning for public health, and has attracted increasing attention in medical information communities. In this study, we propose a novel framework for cancer survival prediction named Multimodal Graph Neural Network (MGNN), which explores the features of real-world multimodual data such as gene expression, copy number alteration and clinical data in a unified framework. In order to explore the inherent relation, we first construct the bipartite graphs between patients and multimodal data. Subsequently, graph neural network is adopted to obtain the embedding of each patient on different bipartite graphs. Finally, a multimodal fusion neural layer is designed to fuse the features from different modal data. The output of our method is the classification of short term survival or long term survival for each patient. Experimental results on one breast cancer dataset demonstrate that MGNN outperforms all baselines. Furthermore, we test the trained model on lung cancer dataset, and the experimental results verify the strong robust by comparing with state-of-the-art methods.

The concept of surprise is central to human learning and development. However, compared to accuracy, surprise has received little attention in the IR community, yet it is an essential component of the information seeking process. This workshop brings together researchers and practitioners of IR to discuss the topic of computational surprise, to set a research agenda, and to examine how to build datasets for research into this fascinating topic. The themes in this workshop include discussion of what can be learned from some well-known surprise models in other fields, such as Bayesian surprise; how to evaluate surprise based on user experience; and how computational surprise is related to the newly emerging areas, such as fake news detection, computational contradiction, clickbait detection, etc.

In this paper, we propose a novel k-anonymization scheme to counter deanonymization queries on social networks. With this scheme, all entities are protected by k-anonymization, which means the attackers cannot re-identify a target with confidence higher than 1/k. The proposed scheme minimizes the modification on original networks, and accordingly maximizes the utility preservation of published data while achieving k-anonymization privacy protection. Extensive experiments on real data sets demonstrate the effectiveness of the proposed scheme, where the efficacy of the k-anonymized networks is verified with the distributions of pagerank, betweenness, and their Kolmogorov-Smirnov (K-S) test.

Alignment among protein-protein interaction (PPI) networks largely benefits our understanding in biological researches as it contributes greatly to the uncovering of important information, such as evolutionary conserved pathways, protein complexes and functional orthologs. Global alignment of multiple PPI networks aims at clustering functionally conserved proteins throughout different species, where most traditional methods attempt to achieve results with high overall coverage and consistency. However little attention was paid on the deeper level criteria of k-coverage and especially the k-consistency that we additionally conducted for evaluations, where k indicates the number of species that the proteins in a cluster belong to. In this paper, we propose a novel approach for global alignment of multiple PPI networks which achieved high k-coverage and k-consistency simultaneously in addition to conventional criteria. The evaluations demonstrate the preferable comprehensive strength of our approach against other three state-of-the-art methods on six datasets composed of various numbers of PPI networks from five species.

In the real world, many problems on massive graphs can be mapped to an underlying critical problem of discovering top-k subgraphs. For massive graphs, subgraph queries may have enormous number of matches, and so it is inefficient to compute all matches when only top-k matches are desired. Meanwhile, parallel algorithm is urgent for the scalability of massive graph computing. In this paper, we address the challenges of top-k subgraph query in massive graph. Firstly, we present a new graph matching notion: “approximate graph simulation”. With approximate graph simulation, top-k subgraph query can be customized by appointing a weighted query graph, which provides good flexibility for different application scenarios. Secondly, we propose a parallel top-k subgraph query algorithm at the level of vertex. With such algorithm, each vertex in massive graph obtains its matching state separately without requiring global graph information. In the algorithm, we also design a filter mechanism to speed up the the computation and a aggregation mechanism to obtain top-k vertices for query focus. Using real-life datasets, we experimentally verify that our approach of parallel top-k subgraph query are efficient.

We study decentralized searches in large-scale, self-organized peer-to-peer networks and investigate the influences of network size and degree distribution (neighborhood size) on search efficiency. Experimental results show that searches are efficient and scalable in large networks, especially with large neighborhood sizes (degrees). Analysis of the data supports a proposed scalability model, in which search path length L (efficiency) is proportional to a poly-logarithmic function of network size N, with degree dm(majority neighborhood size) as the log base. The model explains 90% (R2) of variances in search path lengths. Search time (search path length) predicted by the model shows great potential for efficient searches in real-scale networks of up to a billion distributed systems.

Web search engines are important gateways for users to access health information. This study explored whether a search interface based on the Bing API and enabled by Scatter/Gather, a well‐known document‐clustering technique, can improve health information searches. Forty participants without medical backgrounds were randomly assigned to two interfaces: a baseline interface that resembles typical web search engines and a Scatter/Gather interface. Both groups performed two lookup and two exploratory health‐related tasks. It was found that the baseline group was more likely to rephrase queries and less likely to access general‐purpose sites than the Scatter/Gather group when completing exploratory tasks. Otherwise, the two groups did not differ in behavior and task performance, with participants in the Scatter/Gather group largely overlooking the features (key words, clusters, and the recluster function) designed to facilitate the exploration of semantic relationships between information objects, a potentially useful means for users in the rather unfamiliar domain of health. The results suggest a strong effect of users' mental models of search on their use of search interfaces and a high cognitive cost associated with using the Scatter/Gather features. It follows that novel features of a search interface should not only be compatible with users' mental models but also provide sufficient affordance to inform users of how they can be used. Compared with the interface, tasks showed more significant impacts on search behavior. In future studies, more effort should be devoted to identify salient features of health‐related information needs.

With the ubiquitous production, distribution and consumption of information, today's digital environments such as the Web are increasingly large and decentralized. It is hardly possible to obtain central control over information collections and systems in these environments. Searching for information in these information spaces has brought about problems beyond traditional boundaries of information retrieval (IR) research. This article addresses one important aspect of scalability challenges facing information retrieval models and investigates a decentralized, organic view of information systems pertaining to search in large-scale networks. Drawing on observations from earlier studies, we conduct a series of experiments on decentralized searches in large-scale networked information spaces. Results show that how distributed systems interconnect is crucial to retrieval performance and scalability of searching. Particularly, in various experimental settings and retrieval tasks, we find a consistent phenomenon, namely, the Clustering Paradox , in which the level of network clustering (semantic overlay) imposes a scalability limit. Scalable searches are well supported by a specific, balanced level of network clustering emerging from local system interconnectivity. Departure from that level, either stronger or weaker clustering, leads to search performance degradation, which is dramatic in large-scale networks.

It is crucial to study basic principles that support adaptive and scalable retrieval functions in large networked environments such as the Web, where information is distributed among dynamic systems. We conducted experiments on decentralized IR operations on various scales of information networks and analyzed effectiveness, efficiency, and scalability of various search methods. Results showed network structure, i.e., how distributed systems connect to one another, is crucial for retrieval performance. Relying on partial indexes of distributed systems, some level of network clustering enabled very efficient and effective discovery of relevant information in large scale networks. For a given network clustering level, search time was well explained by a poly-logarithmic relation to network size (i.e., the number of distributed systems), indicating a high scalability potential for searching in a growing information space. In addition, network clustering only involved local self-organization and required no global control - clustering time remained roughly constant across the various scales of networks.

We proposed and implemented a novel clustering algorithm called LAIR2, which has constant running time average for on-the-fly Scatter/Gather browsing [4]. Our experiments showed that when running on a single processor, the LAIR2 on-line clustering algorithm was several hundred times faster than a parallel Buckshot algorithm running on multiple processors [11]. This paper reports on a study that examined the effectiveness of the LAIR2 algorithm in terms of clustering quality and its impact on retrieval performance. We conducted a user study on 24 subjects to evaluate on-the-fly LAIR2 clustering in Scatter/Gather search tasks by comparing its performance to the Buckshot algorithm, a classic method for Scatter/Gather browsing [4]. Results showed significant differences in terms of subjective perceptions of clustering quality. Subjects perceived that the LAIR2 algorithm produced significantly better quality clusters than the Buckshot method did. Subjects felt that it took less effort to complete the tasks with the LAIR2 system, which was more effective in helping them in the tasks. Interesting patterns also emerged from subjects' comments in the final open-ended questionnaire. We discuss implications and future research.

This paper presents the results of an analysis and visualization of 428,440 movies from the Internet Movie Database (IMDb) provided for the Graph Drawing 2005 contest. Simple statistics are presented as well as a tapestry of all movies with an overlay of the giant component of the co-actor network. Academy award winners are highlighted. Major insights are discussed.

In this study, we crawled a local Web domain, created its graph representation, and analyzed the network structure. The results of network analysis revealed local scale-free patterns consistent with previous research on the Web. To discover topical communities of the local domain, link- based co-citation analysis was performed to measure pair-wise similarities. Based on the co-citation graph, a visualization was produced to map the networked domain semantically. All of this offers a way to investigate a local Web structure and to make it more intuitively understandable.

This paper presents a novel approach (1) to define, analyze, and map a scientific discipline and (2) to compare and map the expertise of single authors based on personal bibliography files, e.g., bibtex or EndNote files. Section one motivates this research and relates it to existing work. Section two explains the general procedure from data harvesting, parsing, cleaning via the analysis and mapping of the data to the interpretation of results. To illustrate the new approach, we asked major experts on 'network science' to share their bibtex or EndNote files with us. Using this data set we exemplify data harvesting, data cleaning and integration; give simple statistics, analysis and visualization results such as a map of the network science discipline based on co-author networks and a map of the content coverage and overlay of contributing experts. We conclude with a discussion of challenges and opportunities as well as planned future work