Data Mining and Knowledge Discovery最新文献

Abstract

The detection of central nodes in a network is a fundamental task in network science and graph data analysis. During the past decades, numerous centrality measures have been presented to characterize what is a central node. However, few studies address this issue from a statistical inference perspective. In this paper, we formulate the central node identification issue as a weighted kernel density estimation problem on graphs. Such a formulation provides a generic framework for recognizing central nodes. On one hand, some existing centrality evaluation metrics can be unified under this framework through the manipulation of kernel functions. On the other hand, more effective methods for node centrality assessment can be developed based on proper weighting coefficient specification. Experimental results on 20 simulated networks and 53 real networks show that our method outperforms both six prior state-of-the-art centrality measures and two recently proposed centrality evaluation methods. To the best of our knowledge, this is the first piece of work that addresses the central node identification issue via weighted kernel density estimation.

Change detection is of fundamental importance when analyzing data streams. Detecting changes both quickly and accurately enables monitoring and prediction systems to react, e.g., by issuing an alarm or by updating a learning algorithm. However, detecting changes is challenging when observations are high-dimensional. In high-dimensional data, change detectors should not only be able to identify when changes happen, but also in which subspace they occur. Ideally, one should also quantify how severe they are. Our approach, ABCD, has these properties. ABCD learns an encoder-decoder model and monitors its accuracy over a window of adaptive size. ABCD derives a change score based on Bernstein’s inequality to detect deviations in terms of accuracy, which indicate changes. Our experiments demonstrate that ABCD outperforms its best competitor by up to 20% in F1-score on average. It can also accurately estimate changes’ subspace, together with a severity measure that correlates with the ground truth.

With the rise of Web 2.0 platforms such as online social media, people’s private information, such as their location, occupation and even family information, is often inadvertently disclosed through online discussions. Therefore, it is important to detect such unwanted privacy disclosures to help alert people affected and the online platform. In this paper, privacy disclosure detection is modeled as a multi-label text classification (MLTC) problem, and a new privacy disclosure detection model is proposed to construct an MLTC classifier for detecting online privacy disclosures. This classifier takes an online post as the input and outputs multiple labels, each reflecting a possible privacy disclosure. The proposed presentation method combines three different sources of information, the input text itself, the label-to-text correlation and the label-to-label correlation. A double-attention mechanism is used to combine the first two sources of information, and a graph convolutional network is employed to extract the third source of information that is then used to help fuse features extracted from the first two sources of information. Our extensive experimental results, obtained on a public dataset of privacy-disclosing posts on Twitter, demonstrated that our proposed privacy disclosure detection method significantly and consistently outperformed other state-of-the-art methods in terms of all key performance indicators.

We propose the use of a deep learning architecture, called RETINA, to predict multi-alternative, multi-attribute consumer choice from eye movement data. RETINA directly uses the complete time series of raw eye-tracking data from both eyes as input to state-of-the art Transformer and Metric Learning Deep Learning methods. Using the raw data input eliminates the information loss that may result from first calculating fixations, deriving metrics from the fixations data and analysing those metrics, as has been often done in eye movement research, and allows us to apply Deep Learning to eye tracking data sets of the size commonly encountered in academic and applied research. Using a data set with 112 respondents who made choices among four laptops, we show that the proposed architecture outperforms other state-of-the-art machine learning methods (standard BERT, LSTM, AutoML, logistic regression) calibrated on raw data or fixation data. The analysis of partial time and partial data segments reveals the ability of RETINA to predict choice outcomes well before participants reach a decision. Specifically, we find that using a mere 5 s of data, the RETINA architecture achieves a predictive validation accuracy of over 0.7. We provide an assessment of which features of the eye movement data contribute to RETINA’s prediction accuracy. We make recommendations on how the proposed deep learning architecture can be used as a basis for future academic research, in particular its application to eye movements collected from front-facing video cameras.

Session-based recommendation (SR) aims to dynamically recommend items to a user based on a sequence of the most recent user-item interactions. Most existing studies on SR adopt advanced deep learning methods. However, the majority only consider a special behavior type (e.g., click), while those few considering multi-typed behaviors ignore to take full advantage of the relationships between products (items). In this case, the paper proposes a novel approach, called Substitutable and Complementary Relationships from Multi-behavior Data (denoted as SCRM) to better explore the relationships between products for effective recommendation. Specifically, we firstly construct substitutable and complementary graphs based on a user’s sequential behaviors in every session by jointly considering ‘click’ and ‘purchase’ behaviors. We then design a denoising network to remove false relationships, and further consider constraints on the two relationships via a particularly designed loss function. Extensive experiments on two e-commerce datasets demonstrate the superiority of our model over state-of-the-art methods, and the effectiveness of every component in SCRM.

Distilling actionable patterns from large-scale streaming data in the presence of concept drift is a challenging problem, especially when data is polluted with noisy labels. To date, various data stream mining algorithms have been proposed and extensively used in many real-world applications. Considering the functional complementation of classical online learning algorithms and with the goal of combining their advantages, we propose an Online Ensemble Classification (OEC) algorithm to integrate the predictions obtained by different base online classification algorithms. The proposed OEC method works by learning weights of different base classifiers dynamically through the classical Normalized Exponentiated Gradient (NEG) algorithm framework. As a result, the proposed OEC inherits the adaptability and flexibility of concept drift-tracking online classifiers, while maintaining the robustness of noise-resistant online classifiers. Theoretically, we show OEC algorithm is a low regret algorithm which makes it a good candidate to learn from noisy streaming data. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed OEC method.

Handling incomplete multivariate time series is an important and fundamental concern for a variety of domains. Existing time-series imputation approaches rely on basic assumptions regarding relationship information between sensors, posing significant challenges since inter-sensor interactions in the real world are often complex and unknown beforehand. Specifically, there is a lack of in-depth investigation into (1) the coexistence of relationships between sensors and (2) the incorporation of reciprocal impact between sensor properties and inter-sensor relationships for the time-series imputation problem. To fill this gap, we present the Structure-aware Decoupled imputation network (SaD), which is designed to model sensor characteristics and relationships between sensors in distinct latent spaces. Our approach is equipped with a two-step knowledge integration scheme that incorporates the influence between the sensor attribute information as well as sensor relationship information. The experimental results indicate that when compared to state-of-the-art models for time-series imputation tasks, our proposed method can reduce error by around 15%.

Benign parotid tumors follow an indolent course and present as slow-growing painless swelling in the pre-and-infra-auricular areas. The treatment of choice is surgery. Though the gold standard technique is Superficial Parotidectomy, Extracapsular Dissection (ECD) is an alternative option with the same outcome and decreased complications. This study discusses our experience with extracapsular dissection and the surgical nuances for better results. A retrospective study of histologically confirmed cases of pleomorphic adenoma of the parotid gland, who underwent Extracapsular dissection between September 2019 and March 2023, was done. The demographic details, clinical characteristics, and outcomes were evaluated. There were 33 patients, including 16 females and 17 males, with a mean age of 32.75 years. All cases presented as slow-growing painless swelling for a mean duration of 5 years. Most of the tumors (94%) were of size between 2 and 4 cm, with few tumors more than 4 cm. All underwent extracapsular dissection with complete excision. There was only one complication (seroma) and no incidence of facial palsy in our experience with ECD. The goal of a benign parotid surgery is the complete removal of the tumor with minimum complications, which could be achieved with ECD, which has good tumor clearance and lesser rates of complications with good cosmesis. Thus, this minimally invasive parotid surgery could be a worthwhile option in properly selected cases.

The field of time series anomaly detection is constantly advancing, with several methods available, making it a challenge to determine the most appropriate method for a specific domain. The evaluation of these methods is facilitated by the use of metrics, which vary widely in their properties. Despite the existence of new evaluation metrics, there is limited agreement on which metrics are best suited for specific scenarios and domains, and the most commonly used metrics have faced criticism in the literature. This paper provides a comprehensive overview of the metrics used for the evaluation of time series anomaly detection methods, and also defines a taxonomy of these based on how they are calculated. By defining a set of properties for evaluation metrics and a set of specific case studies and experiments, twenty metrics are analyzed and discussed in detail, highlighting the unique suitability of each for specific tasks. Through extensive experimentation and analysis, this paper argues that the choice of evaluation metric must be made with care, taking into account the specific requirements of the task at hand.