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

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial–temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.

/pdf/a-comprehensive-survey-on-graph-neural-networks-4lw9i4v183.pdf

A Comprehensive Survey on Graph Neural Networks

Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data. Meanwhile, most existing representation learning methods embed the heterogeneous graphs into a single geometric space, either Euclidean or hyperbolic. This kind of single geometric view is usually not enough to observe the complete picture of heterogeneous graphs due to their rich semantics and complex structures. Under these observations, this paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL), to better represent the heterogeneous graphs when supervisory data is unavailable. GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures, which is expected to bring in more benefits for downstream tasks. GCL maximizes the mutual information between two geometric views by contrasting representations at both local-local and local-global semantic levels. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines, including both unsupervised methods and supervised methods, on three tasks, including node classification, node clustering and similarity search.

Geometry Contrastive Learning on Heterogeneous Graphs

Recent years have witnessed a dramatic increase of information due to the ever development of modern technologies. The large scale of information makes data analysis, particularly data mining and knowledge discovery tasks, unprecedentedly challenging. First, data is becoming more and more interconnected. In a variety of domains such as social networks, chemical compounds, and XML documents, data is no longer represented by a flat table with instance-feature format, but exhibits complex structures indicating dependency relationships. Second, data is evolving more and more dynamically. Emerging applications such as social networks continuously generate information over time. Third, the learning tasks in many real-life applications become more and more complicated in that there are various constraints on the number of labelled data, class distributions, misclassification costs, or the number of learning tasks etc.
Considering the above challenges, this research aims to investigate theoretical foundations, study new algorithm designs and system frameworks to enable the mining of complex graph streams from three aspects, including (1) Correlated Graph Stream Mining, (2) Graph Stream Classifications, and (3) Complex Task Graph Classification.
In particular, correlated graph stream mining intends to carry out structured pattern search and support the query of similar graphs from a graph stream. Due to the dynamic changing nature of the streaming data and the inherent complexity of the graph query process, treating graph streams as static datasets is computationally infeasible or ineffective. Therefore, we proposed a novel algorithm, CGStream, to identify correlated graphs from a data stream, by using a sliding window, which covers a number of consecutive batches of stream data records. Experimental results demonstrate that the proposed algorithm is several times, or even an order of magnitude, more efficient than the straightforward algorithms.
Graph stream classification aims to build effective and efficient classification models for graph streams with continuous growing volumes and dynamic changes. We proposed two methods for complex graph stream classification. Due to the inherent complexity of graph structure, labelling graph data is very expensive. To solve this problem, we proposed a gLSU algorithm, which aims to select discriminative subgraph features with minimum redundancy by using both labelled and unlabelled graphs for graph streams. The second approach handles graph streams with imbalanced class distributions and noise. Both frameworks use an instance weighting scheme to capture the underlying concept drifts of graph streams and achieve significant performance gain on benchmark graph streams.
Complex task graph classification aims to address the graph classification problems with complex constraints. We studied two complex task graph classification problems, cost-sensitive graph classification of large-scale graphs and multi-task graph classification. As in medical diagnosis the misclassification cost/risk…

/pdf/complex-graph-stream-mining-52wb9k9h0m.pdf

Complex graph stream mining

Social network-based tasks frequently emphasize the influence of direct neighbors on human decision-making. However, there is no objective consensus on whether direct neighbors are influential in all circumstances, or any other type of “neighbors” who have a greater impact. In this study, we investigate the patterns of heterogeneous social influence on human decision-making from the perspectives of opinions, behaviors, preferences and decision probabilities across three large-scale online networks. Our results demonstrate that the influence of similar behavior during exploration on decision-making outperforms that of explicit social relationships regardless of relationship sparsity, yet is associated with shared experiences, network structures, and individual attributes. Specifically, at low levels of experiences, similar behavior during exploration drives human behavioral shifts from bystanders to participants more effectively than explicit social relationships. Further incorporating heterogeneous influence into opinion dynamics through the matrix factorization framework, we reveal the mechanism of heterogeneous social influence acting on decision-making in online networks, with implications for understanding human decision-making. 

How heterogeneous social influence acts on human decision-making in online social networks

Graph neural networks (GNNs) are powerful models to handle graph data and can achieve state-of-the-art in many critical tasks including node classification and link prediction. However, existing graph neural networks still face both challenges of over-smoothing and over-squashing based on previous literature. To this end, we propose a new Curvature-based topology-aware Dropout sampling technique named CurvDrop, in which we integrate the Discrete Ricci Curvature into graph neural networks to enable more expressive graph models. Also, this work can improve graph neural networks by quantifying connections in graphs and using structural information such as community structures in graphs. As a result, our method can tackle the both challenges of over-smoothing and over-squashing with theoretical justification. Also, numerous experiments on public datasets show the effectiveness and robustness of our proposed method. The code and data are released in https://github.com/liu-yang-maker/Curvature-based-Dropout.

CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing

\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the inner model weights and the outer architecture parameter in a weight-sharing supernet. A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation. While much has been discussed about several potentially fatal factors in DARTS, the architecture gradient, a.k.a. hypergradient, has received less attention. In this paper, we tackle the hypergradient computation in DARTS based on the implicit function theorem, making it only depends on the obtained solution to the inner-loop optimization and agnostic to the optimization path. To further reduce the computational requirements, we formulate a stochastic hypergradient approximation for differentiable NAS, and theoretically show that the architecture optimization with the proposed method, named iDARTS, is expected to converge to a stationary point. Comprehensive experiments on two NAS benchmark search spaces and the common NAS search space verify the effectiveness of our proposed method. It leads to architectures outperforming, with large margins, those learned by the baseline methods.

Shirui Pan

Papers

Geometry Contrastive Learning on Heterogeneous Graphs

Complex graph stream mining

How heterogeneous social influence acts on human decision-making in online social networks

CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing

iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients