Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

Social Network Analysis

We study the problem of representation learning in heterogeneous networks. Its unique challenges come from the existence of multiple types of nodes and links, which limit the feasibility of the conventional network embedding techniques. We develop two scalable representation learning models, namely metapath2vec and metapath2vec++. The metapath2vec model formalizes meta-path-based random walks to construct the heterogeneous neighborhood of a node and then leverages a heterogeneous skip-gram model to perform node embeddings. The metapath2vec++ model further enables the simultaneous modeling of structural and semantic correlations in heterogeneous networks. Extensive experiments show that metapath2vec and metapath2vec++ are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, such as node classification, clustering, and similarity search, but also discern the structural and semantic correlations between diverse network objects.

https://dl.acm.org/doi/pdf/10.1145/3097983.3098036

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

The Analysis of Time Series: An Introduction, 4th edn. By C. Chatfield. ISBN 0 412 31820 2. Chapman and Hall, London, 1989. 242 pp. £13.50.

The Analysis of Time Series: An Introduction

Identifying effective drug treatments for COVID-19 is essential to reduce morbidity and mortality. Although a number of existing drugs have been proposed as potential COVID-19 treatments, effective data platforms and algorithms to prioritize drug candidates for evaluation and application of knowledge graph for drug repurposing have not been adequately explored. A COVID-19 knowledge graph by integrating 14 public bioinformatic databases containing information on drugs, genes, proteins, viruses, diseases, symptoms and their linkages is developed. An algorithm is developed to extract hidden linkages connecting drugs and COVID-19 from the knowledge graph, to generate and rank proposed drug candidates for repurposing as treatments for COVID-19 by integrating three scores for each drug: motif scores, knowledge graph PageRank scores, and knowledge graph embedding scores. The knowledge graph contains over 48 000 nodes and 13 37 000 edges, including 13 563 molecules in the DrugBank database. From the 5624 molecules identified by the motif-discovery algorithms, ranking results show that 112 drug molecules had the top 2% scores, of which 50 existing drugs with other indications approved by health administrations reported. The proposed drug candidates serve to generate hypotheses for future evaluation in clinical trials and observational studies.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/adtp.202100055

Drug Repurposing for the Treatment of COVID-19: A Knowledge Graph Approach

This paper studies the constrained-space probabilistic threshold range query (CSPTRQ) for moving objects, where objects move in a constrained-space (i.e., objects are forbidden to be located in some specific areas), and objects' locations are uncertain. We differentiate two forms of CSPTRQs: explicit and implicit ones. Specifically, for each moving object o, we model its location uncertainty as a closed region, u, together with a probability density function. We also model a query range, R, as an arbitrary polygon. An explicit query can be reduced to a search (over all the u) that returns a set of tuples in form of (o, p) such that p ? pt, where p is the probability of o being located in R, and 0≤pt ≤ 1 is a given probabilistic threshold. In contrast, an implicit query returns only a set of objects (without attaching the specific probability information), whose probabilities being located in R are higher than pt. The CSPTRQ is a variant of the traditional probabilistic threshold range query (PTRQ). As objects moving in a constrained-space are common, clearly, it can also find many applications. At the first sight, our problem can be easily tackled by extending existing methods used to answer the PTRQ. Unfortunately, those classical techniques are not well suitable for our problem, due to a set of new challenges. Another method used to answer the constrained-space probabilistic range query (CSPRQ) can be easily extended to tackle our problem, but a simple adaptation of this method is inefficient, due to its weak pruning/validating capability. To solve our problem, we develop targeted solutions that are easy-to-understand and also easy-to-implement. Our central idea is to swap the order of geometric operations and to compute the appearance probability in a multi-step manner. We demonstrate the efficiency and effectiveness of the proposed methods through extensive experiments. Meanwhile, from the experimental results, we further perceive the difference between explicit and implicit queries; this finding is interesting and also meaningful especially for the topics of other types of probabilistic threshold queries.

SMe: explicit & implicit constrained-space probabilistic threshold range queries for moving objects

Spatial objects associated with keywords are prevalent in applications such as Google Maps and Twitter. Recently, the topic of spatial keyword queries has received plenty of attention. Spatial Group Keyword (SGK) search is a popular class of queries; their goal is to find a set of objects which are close to each other and are associated to a set of input keywords. In this paper, we propose SpaceKey, a system for retrieving and visualizing spatial objects returned by SGK queries. In addition to existing SGK query types, SpaceKey supports a novel query, called SPM query. An SPM query is defined by a spatial pattern, a graph whose vertices contain keywords and its edges are associated with distance constraints. The results are sets of objects that match the pattern. SpaceKey allows users to perform comparison analysis between different SGK query types. We plan to make SpaceKey an open-source web-based platform, and design API functions for software developers to plug other SGK query algorithms into our system.

SpaceKey: Exploring Patterns in Spatial Databases

Heterogeneous information networks (HINs), which are typed graphs with labeled nodes and edges, have attracted tremendous interest from academia and industry. Given two HIN nodes s and t, and a natural number k, we study the discovery of the k most important paths in real time. The paths found can be used to support friend search, product recommendation, anomaly detection, and graph clustering. Although related algorithms have been proposed before, they were primarily designed to return the k shortest paths from unlabeled graphs. This leads to two problems: (1) there are often many shortest paths between s and t, and so it is not easy to choose the k best ones; and (2) it is arguable whether a shorter path implies a more crucial one. To address these issues, we study the top-k meta path query for a HIN. A meta path abstracts multiple path instances into a high-level path pattern, thereby giving more insight between two nodes. We further study several ranking functions that evaluate the importance of meta paths based on frequency and rarity, rather than on path length. We propose a solution that seamlessly integrates these functions into an A* search framework. The connectivity experiment on ACM dataset shows that our proposed method outperforms state-of-the-art algorithms.

Evaluating Top-k Meta Path Queries on Large Heterogeneous Information Networks

Given a set O of objects and a query point q on a road network, the k Nearest Neighbor (kNN) query returns the k nearest objects in O with the shortest road network distance to q. These kNN queries find many applications in location-based services, e.g., ride-hailing services, where each taxi is regarded as an object. In such applications, objects are constantly moving such that even for the same query point, the correct answer of a kNN query may vary with time. Ideally, the returned answer should be adequately correct with respect to the moving object set. However, in literature, all existing solutions for kNN queries mainly focus on reducing the query time, indexing storage, or throughput of the kNN queries with little focus on their correctness. Motivated by this, we propose a framework on correctness-aware kNN queries which aim to optimize system throughput while guaranteeing query correctness on moving objects. We formally define the serializable-kNN query that ensures the correctness of the query answer when considering moving objects and dependencies of different queries. We propose several techniques to optimize the throughput of serializable-kNN queries: firstly, we propose efficient index structures and new query algorithms that significantly improve the throughput; we further present novel scheduling algorithms that aim to avoid conflicts and improve the system throughput. Moreover, we devise approximate solutions that provide a controllable trade-off between the correctness of kNN queries and system throughput. Extensive experiments on real-world data demonstrate the effectiveness and efficiency of our proposed solutions over alternatives.

Reynold Cheng

Papers

Drug Repurposing for the Treatment of COVID-19: A Knowledge Graph Approach

SMe: explicit & implicit constrained-space probabilistic threshold range queries for moving objects

SpaceKey: Exploring Patterns in Spatial Databases

Evaluating Top-k Meta Path Queries on Large Heterogeneous Information Networks

An Efficient Framework for Correctness-Aware kNN Queries on Road Networks