WORKSHOP INFORMATION

The 2nd EYRE workshop welcomes contributions related to any aspect of entity retrieval and semantic search. We also organize two shared tasks: entity summarization and entity search.

The first Workshop on Model Selection and Parameter Tuning in Recommender Systems @ CIKM 2019 is a place for discussing and exchanging recent advances and open challenges between the Model-Selection and Parameter Tuning community and Recommendation Systems community. Recommender systems have attracted strong attention of the machine learning community, especially within the last decades. Researchers have developed various algorithms proven to have good performance in the laboratory environment; however, applying them to real business cases is typically more difficult. This workshop addresses the issues of algorithm selection and parameter tuning for recommender systems. The goal is to bring together researchers from the machine learning community with the industry representatives in order to exchange information on current challenges, constraints and ideas from both domains.

Data-enabled smart transportation has attracted a surge of interest from machine learning and data mining researchers nowadays due to the bloom of online ride-hailing industry and rapid development of autonomous driving. Large-scale high quality route data and trading data (spatiotemporal data) have been generated every day, which makes AI an urgent need and preferred solution for the decision making in intelligent transportation systems. While a large of amount of work have been dedicated to traditional transportation problems, they are far from satisfactory for the rising need.

We propose a half-day workshop at CIKM 2019 for the professionals, researchers, and practitioners who are interested in mining and understanding big and heterogeneous data generated in transportation, and AI applications to improve the transportation system.

The BigScholar 2019 workshop aims at bringing together academics and practitioners from diverse fields to share ideas and experience with management, analysis, mining, and applications of big scholarly data. The goal is to contribute to the birth of a community having a shared interest around big scholarly data and exploring it using knowledge discovery, data science and analytics, network science, and other appropriate technologies.

Now we are living in an interconnected world - where most of the data, informational objects, agents, or components are interconnected or interact with each other - forming gigantic and sophisticated information networks. Most real-world applications based on information networks can be structured into heterogeneous information networks that include different types of objects or links. Recent works on heterogeneous information network analysis and its applications have led to a convergence of methodologies for network modeling, graph mining, linking analysis, data semantics mining, and incorporating classification, learning and reasoning with graphical models. As a promising network analysis paradigm, heterogeneous information network analysis also faces challenges, such as how to manage more complex heterogonous data like RDF data and how to quickly handle large-scale heterogonous information network. This workshop shall provide a forum for researchers and practitioners to share new techniques and applications in heterogonous information network analysis.

The main focus of this workshop is to bring proposals and insights that demonstrate the knowledge-driven technologies, developments and applications for ensuring improvement of human quality of life. The intended thrust is to promote the development of human-centric intelligent technologies like precise and personalized medication and prognosis prediction, improved elderly care, minimizing private data theft, knowledge-driven energy and resource management, deep learning and artificial intelligence based applications for risk prediction and augmented human capability generation. We expect researchers in the field of knowledge management, information retrieval, artificial intelligence, data mining, privacy analytics will provide insights of technological aspects as well as application-specific scenarios of human-centric knowledge-driven analytics and systems. The areas of interest, not limited to: Clinical Analytics; Privacy Preserving Data Mining; Recommender systems for retail, financial decision making; Fraud detection and prevention system; Human cognition analysis; Knowledge-driven human action understanding and decision making; Deep learning and artificial intelligence based applications; Social network analysis and related others.

The workshop focuses on all the aspects related to the injection and adoption of knowledge sources in Recommender Systems. More and more precise and powerful recommendation algorithms and techniques have been proposed over the last years able to effectively assess users' tastes and predict information that would probably be of interest for them. Most of these approaches rely on the collaborative paradigm (often exploiting machine learning techniques) and do not take into account the huge amount of knowledge, both structured and non-structured ones, describing the domain of interest for the recommendation engine. The aim of knowledge-aware and conversational recommender systems is to go beyond the traditional accuracy goal and to start a new generation of algorithms and interactive approaches which exploit the knowledge encoded in ontological and logic-based knowledge bases, knowledge graphs as well as the semantics emerging from the analysis and exploitation of semi-structured textual sources.

Graph structured data are ubiquitous nowadays in a variety of disciplines and domains ranging from computer science, social science, economics, medicine, to bioinformatics. Examples include social networks, knowledge graph, e-commerce networks, protein-protein interaction graphs, and molecular structures. Recently, representation learning for graphs has attracted considerable attention from researchers and communities, and led to state-of-the-art results in numerous tasks including molecule classification, new drug discovery, recommender systems, etc. This workshop aims to provide a forum for industry and academia to discuss the latest progress on graph representation learning and their applications in different fields. We expect novel research works that address various aspects of graph representation learning, including learning representations of entire graph, knowledge graph embedding, graph neural networks, applications in information network analysis, natural language understanding, recommender systems, drug discovery, and so on.

The rapid growth of medical and health informatics field is tightly coupled with developments within several areas in computer science, including data and text mining, information extraction and database management systems, among others. A fundamental topic of research within medical informatics is how to make effective use of the tremendous amount of biological and biomedical data to improve the understanding of biological systems. Such data include, but are ot limited to, gene and protein sequences, gene expression profiles, protein structure predictions resulting from high-throughput computational methods, protein-protein interactions from proteomic studies, Single Nucleotide Polymorphisms (SNPs) profiles, and information from the literature and other textual resources. The need to extract, understand, integrate, and make use of nformation embedded in such heterogeneous unstructured data, automatically and effectively drives the current research in medical and healthcare informatics.

The focus of this workshop is to bring together researchers that work in the areas of data and text mining and computational biology, interested in integrating such heterogeneous structured and unstructured data, while effectively using literature information in medical informatics solutions. The workshop will focus on:

1. Medical and health informatics-oriented data and text mining solutions that utilize relevant background knowledge from text (including scientific publications, EHRs, and database annotations). Such approaches range from term/concept recognition, association mining to event or relation extraction, i.e. gene-disease associations, protein-protein interactions, drug-drug interactions, etc.

2. Knowledge discovery methods, that consolidate and process heterogeneous biomedical data collected from electronic bulletin boards, EHRs, scientific publications, and other types of experiments.

3. Development of computational methods to solve a medical unmet issue via big-data analytics and machine learning approaches.

Developing computational tools and methods mainly contribute to a better understanding of biological systems is still challenging. However, understanding of both omics data and text mining and biomedicine is essential for realizing precision medicine, tailored therapy. Thus, identification and definition of the relevant computational and biological problems, as well as development of evaluation methods for related text-mining tools are ongoing efforts.