Recent studies give more attention to the anomaly detection (AD) methods that can leverage a handful of labeled anomalies along with abundant unlabeled data. These existing anomaly-informed AD methods rely on manually predefined score target(s), e.g., prior constant or margin hyperparameter(s), to realize discrimination in anomaly scores between normal and abnormal data. However, such methods would be vulnerable to the existence of anomaly contamination in the unlabeled data, and also lack adaptation to different data scenarios.

Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud computing. However, most of the current research tends to view deep AD algorithms as a whole, without dissecting the contributions of individual design choices like loss functions and network architectures. This view tends to diminish the value of preliminary steps like data preprocessing, as more attention is given to newly designed loss functions, network architectures, and learning paradigms. In this paper, we aim to bridge this gap by asking two key questions: (i) Which design choices in deep AD methods are crucial for detecting anomalies? (ii) How can we automatically select the optimal design choices for a given AD dataset, instead of relying on generic, pre-existing solutions? To address these questions, we introduce ADGym, a platform specifically crafted for comprehensive evaluation and automatic selection of AD design elements in deep methods. Our extensive experiments reveal that relying solely on existing leading methods is not sufficient. In contrast, models developed using ADGym significantly surpass current state-of-the-art techniques.

Recognizing terminology entities across domains from professional texts is an important but challenging task in NLP. Most existing methods focus on recognizing generic entities, but few methods are to recognize the domain-specific entities across domains due to the very large discrepancy of entity representations between the source and target domains. To address this issue, we introduce domain vectors and context vectors to represent domain-specific semantics of entities and domain-irrelevant semantics of the context words, respectively. Based on the two types of vectors, we present a simple yet effective novel cross-domain named entity recognition approach, which aligns entity distributions between domains and separates entity distributions from context distributions for easily identifying entities. Experimental results demonstrate that the proposed approach can obtain significant improvement compared to existing cross-domain NER methods.

Current text classification methods typically encode the text merely into embedding before a naive or complicated classifier, which ignores the suggestive information contained in the label text. As a matter of fact, humans classify documents primarily based on the semantic meaning of the subcategories. We propose a novel model structure via siamese BERT and interactive double attentions named IDEA (Interactive DoublE Attentions) to capture the information exchange of text and label names. Interactive double attentions enable the model to exploit the inter-class and intra-class information from coarse to fine, which involves distinguishing among all labels and matching the semantical subclasses of ground truth labels. Our proposed method outperforms the state-of-the-art methods using label texts significantly with more stable results.

Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data? In this work, we answer these key questions by conducting (to our best knowledge) the most comprehensive anomaly detection benchmark with 30 algorithms on 57 benchmark datasets, named ADBench. Our extensive experiments (98,436 in total) identify meaningful insights into the role of supervision and anomaly types, and unlock future directions for researchers in algorithm selection and design. With ADBench, researchers can easily conduct comprehensive and fair evaluations for newly proposed methods on the datasets (including our contributed ones from natural language and computer vision domains) against the existing baselines. To foster accessibility and reproducibility, we fully open-source ADBench and the corresponding results.

Representing the true label as one-hot vector is the common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instance and labels, as labels are often not completely independent and instances may relate to multiple labels in practice. The inadequate one-hot representations tend to train the model to be over-confident, which may result in arbitrary prediction and model overfitting, especially for confused datasets (datasets with very similar labels) or noisy datasets (datasets with labeling errors). While training models with label smoothing can ease this problem in some degree, it still fails to capture the realistic relation among labels. In this paper, we propose a novel Label Confusion Model (LCM) as an enhancement component to current popular text classification models. LCM can learn label confusion to capture semantic overlap among labels by calculating the similarity between instance and labels during training and generate a better label distribution to replace the original one-hot label vector, thus improving the final classification performance. Extensive experiments on five text classification benchmark datasets reveal the effectiveness of LCM for several widely used deep learning classification models. Further experiments also verify that LCM is especially helpful for confused or noisy datasets and superior to the label smoothing method.

In mobile ad hoc networks (MANETs), service composition faces severe challenges such as the lack of central server, node mobility and wireless network failure, which are usually not considered in web service composition on Internet. This paper designs and implements an on-demand service composition protocol for MANETs with consideration of quality of service (QoS). Based on the well-known Dynamic Source Routing (DSR) protocol, we construct various control messages for discovering, invoking and maintaining composite services, and use a distributed message processing flow for handling and transmitting the service composition messages. In our experiments, the proposed protocol has been implemented based on Jist/Swans ad hoc network simulator.

Mobile computing environments pose two challenging problems for the design and configuration of mobile services: constant changes of computation contexts and resource limitation of mobile devices. This paper presents a dynamic software configuration approach implemented by using different design paradigms during execution time. After analyzing the features of these paradigms, we propose the selection rules of design paradigms under different contexts, which are used to dynamically reconfigure mobile services to adapt to environmental changes and meet the users' requirements. The rules make the automatic or semi-automatic software configuration possible. To conserve resources, we present an optimal software partitioning algorithm based on network flow theory to optimize the design paradigms. Finally, a case study shows the flexibility and effectiveness of our approach

A traditional application with only one design paradigm can not well adapt to the constant variations of contexts and user preferences in pervasive computing. In this paper, we argue that a pervasive computing application should support multiple design paradigms and present an approach to dynamically selecting the most appropriate paradigm at runtime according to environmental changes. Based on analyzing the characteristics of adaptive software architecture, this paper presents the general paradigm selection rules which can be combined with the specific context to automatically or semi-automatically create the applicable software (re)configuration strategies. For mobile components paradigm, a novel heuristic software partitioning algorithm is proposed to reasonably allocate a pervasive computing application among machines for resource conservation. Finally, we discuss a case study that demonstrates the flexibility and effectiveness of our approach

The rapid popularity of wireless networks and portable devices spurs mobile users to access various information services. Service provision in ubiquitous computing has become a challenging issue. In this paper, we present a user-centric service provision model (TJCSPM). UCSPM is designed to support user-oriented quality of service (QoS) evaluation and dynamic service delivery, according to various contexts such as device capability, network status and user preference, etc. Unlike most service provision middleware, UCSPM can provide appropriate services to mobile users, which are not only suitable for being delivered to resource-limited environments, but also with a high degree of satisfaction of users. We have developed a prototype of context-aware expo assistant application to demonstrate the effectiveness of UCSPM.

Distributed applications operating in pervasive computing environment should have abilities to cope with the high heterogeneity and variability of this environment. In a high abstract level, the dynamic software architecture can be used to provide the flexibility and adaptation for the applications by modifying the structure of software, such as adding, removing, replacing components, in the execution time. Besides, mobile codes technologies have provided ability to move around for components. However, software architecture supporting component migration has not been deeply studied. In this paper, an adaptable software architecture for pervasive computing is introduced. We revisit software architecture, and describe its elements related to mobility, especially components and connectors, in formal forms. Due to the components’ correlation, the migration relationships between two components are proposed and discussed in detail. As an example, multiple notable design paradigms are expressed in a unified way by using our mobile component approach, which shows the effectiveness and generality of our model.