Recently, rule-based time series classification models are widely used in safety-critical scenarios demanding strong interpretability, through providing explicit and rigorous rationales. However, due to the discrepancy between discrete rules and continuous neural networks, the generated rules are not completely consistent with the actual decision-making process, rendering users hesitant to trust the model. Additionally, existing methods learn the role (weight) of each time point independently, which is not in line with human understanding and the consecutive nature of temporal properties. In this paper, we propose a novel neuro-symbolic model named TemporalRule, aiming to automatically learn Signal Temporal Logic (STL) rules for interpretable time series classification. Our model directly optimizes the neural networks representing discrete rules via gradient grafting, producing reliable rules that can exactly determine the classification results. Notably, a temporal logical layer is designed to simulate expressive temporal operators, including one 2-predicate operator (Until) and two 2-level composite operators (EA and AE), through adaptively learning the time bounds of involved intervals. That creates consistent weights for consecutive time points, enhancing the intuitiveness of derived rules. Extensive experiments on diverse real-world datasets in safety-critical domains show that TemporalRule achieves superior and stable classification accuracy compared to state-of-the-art rule-based approaches, and the learned rules can precisely and concisely explicate the classification results, leading to a trustable model.

The rapid growth of the Internet of Things (IoT) has resulted in an explosive increase in time-series data, making time-series databases (TSDBs) such as InfluxDB and OpenTSDB essential components in IoT ecosystems.At the same time, the decreasing cost of SSDs has facilitated their increasing adoption in large-scale data centers.Traditional TSDBs are primarily based on Log-Structured Merge Tree (LSM-tree) optimized for HDDs, which convert random reads and writes into sequential ones.However, these systems fail to fully exploit the unique characteristics of SSDs, such as random I/O operations and internal parallelism.In this paper, we present ReefsDB, an LSM-tree-based TSDB that is highly optimized for SSDs and implemented using the Rust programming language.We evaluate ReefsDB using the Time Series Benchmark Suite for write-intensive workloads, and the results demonstrate that ReefsDB is 2.9×∼3.2×faster than InfluxDB in write performance, while reducing read latencies by 27%∼62%.

Graphs constructed from real-world scenarios are often incomplete due to privacy restrictions or resource limitations, posing significant challenges for node classification, especially when labeled data are scarce. In many scenarios of incomplete graphs, the real node degrees, such as the number of followers in social networks or publications' references in citation networks, are easily accessible and informative, which could indicate the degree of incompleteness. However, most of existing researches of incomplete graphs focus on edge completion, but ignore the node completion with known node degrees. In this paper, we propose a new few-shot node classification problem on incomplete graphs with real node degrees. To deal with node completion, edge completion and label completion of this problem, we develop an effective Large Language Models (LLMs) empowered Graph Convolutional Network (GCN) model utilizing the real node Degrees, namely LLMDGCN. First, we leverage LLMs to initially fill in the missing nodes and labels. Next, we design an edge prediction module that employs the real node degrees and inter-category probability matrix to recover the missing edges for each node. We then iteratively train the GCN and the edge prediction module. The GCN generates pseudo labels, which the edge prediction module uses to restore edges, and these edges are fed back into the GCN to improve accuracy. Extensive experiments on four benchmark datasets demonstrate the effectiveness and robustness of our proposed method for the few-shot node classification on incomplete graphs with real node degrees.

Accurately forecasting traffic flow using time-series data from multimedia sensors remains a significant challenge, despite its importance for advancing intelligent transportation systems. Recent advancements in attention-based models have shown promise in capturing spatial-temporal dependencies in traffic flow data. Yet, these models exhibit three principal limitations: (1) they employ either factorized or coupled spatial-temporal attention mechanisms, potentially failing to fully harness the potential of these distinct approaches; (2) the attention allocation for spatial nodes is predominantly data-centric, which may overlook existing knowledge about the nodes' importance within the transportation network; (3) while traditional attention-based methods effectively capture long-term dependencies, they often struggle with adapting to the disparate lengths of temporal contexts. To overcome these limitations, we introduce a multi-way framework dubbed FEST that innovatively integrates both factorized and coupled spatial-temporal attention mechanisms. We then enhance FEST by incorporating PageRank-derived node importance scores to guide focus on nodes. Moreover, a novel multi-scale temporal learning approach is proposed to improve model capability with both long- and short-term temporal dynamics. Extensive experiments on real-world datasets under long- and short-term prediction scenarios confirm the effectiveness of our method.

A modality gap exists between infrared and visible images, presenting challenges for image fusion. Despite the modality heterogeneity, both types of images inherently capture the same scene, suggesting the presence of common information. Effectively extracting shared features while distinguishing modality-specific ones is pivotal for bridging this gap and achieving superior fusion outcomes. To address this, we propose the S hared-S pecific F usion Net work (S2F-Net). The S2F-Net introduces a three-branch feature extractor, which retains two branches for extracting features from each modality, innovatively creating an additional branch dedicated to facilitating the separation of shared features from modality-specific ones. This facilitates guiding the fusion of cross-modal information to generate efficient fusion features, ensuring the effective integration of complementary information from different modalities. To achieve feature fusion and image reconstruction, we propose two fusion modules: the Cross-modality Attention-Guided Fusion Module (CAGFM) and the Multi-Level Fusion Module (MLFM). The former utilizes shared and specific features by employing cross-modality channel attention, enabling effective integration of information across modalities. The latter facilitates feature interaction across different levels. Additionally, to effectively disentangle shared and specific features, we introduce the shared-specific learning module. Extensive experiments conducted on open-source datasets validate the superior performance of our proposed method.

Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment, since it requires only a limited set of seed words (label names) for each category instead of labeled data. With the help of recently popular prompting Pre-trained Language Models (PLMs), many studies leveraged manually crafted and/or automatically identified verbalizers to estimate the likelihood of categories, but they failed to differentiate the effects of these category-indicative words, let alone capture their correlations and realize adaptive adjustments according to the unlabeled corpus. In this paper, in order to let the PLM effectively understand each category, we at first propose a novel form of rule-based knowledge using logical expressions to characterize the meanings of categories. Then, we develop a prompting PLM-based approach named RulePrompt for the WSTC task, consisting of a rule mining module and a rule-enhanced pseudo label generation module, plus a self-supervised fine-tuning module to make the PLM align with this task. Within this framework, the inaccurate pseudo labels assigned to texts and the imprecise logical rules associated with categories mutually enhance each other in an alternative manner. That establishes a self-iterative closed loop of knowledge (rule) acquisition and utilization, with seed words serving as the starting point. Extensive experiments validate the effectiveness and robustness of our approach, which markedly outperforms state-of-the-art weakly supervised methods. What is more, our approach yields interpretable category rules, proving its advantage in disambiguating easily-confused categories.

Anomaly detection, particularly the detection of anomalous behaviors in dynamic and heterogeneous social networks, is becoming more and more crucial in real life. Traditional rule-based and feature-based methods cannot well capture the structural and temporal patterns of ever-changing user behaviors. Moreover, most of the existing works based on network embedding either rely on discretized snapshots, which have ignored accurate temporal relations among user behaviors and weakened the impact of new edges, or fail to utilize dynamic and heterogeneous information simultaneously to distinguish varying effects of new edges on existing nodes. In this paper, we propose an end-to-end continuous-time model, named Temporal Heterogeneous Graph Neural Network (THGNN), to detect anomalous behaviors (edges) in dynamic heterogeneous social networks. Specifically, the model constantly updates node embeddings by propagating the information of a new edge to its source and target nodes as well as their neighbors. In this process, heterogeneous encoders are employed to handle different types of nodes and edges. What is more, a novel dual-level distributive attention mechanism is designed to allocate the influence degree of a currently interacting node to its multiple neighbors, considering the combined effect of edge type and time interval information. That can be regarded as an extension of the classical aggregative attention mechanism in the opposite direction. Extensive experiments on four real-world datasets demonstrate that THGNN outperforms all the baselines on the task of anomalous edge detection, achieving an average AUC gain of 6% across all datasets.

Continual text classification is an important research direction in Web mining. Existing works are limited to supervised approaches relying on abundant labeled data, but in the open and dynamic environment of Internet, involving constant semantic change of known topics and the appearance of unknown topics, text annotations are hard to access in time for each period. That calls for the technique of weakly supervised text classification (WSTC), which requires just seed words for each category and has succeed in static text classification tasks. However, there are still no studies of applying WSTC methods in a continual learning paradigm to actually accommodate the open and evolving Internet. In this paper, we tackle this problem for the first time and propose a framework, named Continual Learning for Weakly Supervised Text Classification (CL-WSTC), which can take any WSTC method as base model. It consists of two modules, classification decision with delay and seed word updating. In the former, the probability threshold for each category in each period is adaptively learned to determine the acceptance/rejection of texts. In the latter, with candidate words output by the base model, seed words are added and deleted via reinforcement learning with immediate rewards, according to an empirically certified unsupervised measure. Extensive experiments show that our approach has strong universality and can achieve a better trade-off between classification accuracy and decision timeliness compared to non-continual counterparts, with intuitively interpretable updating of seed words.

Relation classification (RC) is an important task in knowledge extraction from texts, while data-driven approaches, although achieving high performance, heavily rely on a large amount of annotated training data. Recently, many few-shot RC models have been proposed and yielded promising results in general domain datasets, but when adapting to a specific domain, such as medicine, the performance drops dramatically. In this paper, we propose a Knowledge-Enhanced Few-shot RC model for the Domain Adaptation task (KEFDA), which incorporates general and domain-specific knowledge graphs (KGs) to the RC model to improve its domain adaptability. With the help of concept-level KGs, the model can better understand the semantics of texts and easily summarize the global semantics of relation types from only a few instances. To be more important, as a kind of meta-information, the manner of utilizing KGs can be transferred from existing tasks to new tasks, even across domains. Specifically, we design a knowledge-enhanced prototypical network to conduct instance matching, and a relation-meta learning network for implicit relation matching. The two scoring functions are combined to infer the relation type of a new instance. Experimental results on the Domain Adaptation Challenge in the FewRel 2.0 benchmark demonstrate that our approach significantly outperforms the state-of-the-art models (by 6.63% on average).

Textual documents created and distributed on the Internet are ever changing in various forms. Most of existing works are devoted to topic modeling and the evolution of individual topics, while sequential relations of topics in successive documents published by a specific user are ignored. In this paper, in order to characterize and detect personalized and abnormal behaviors of Internet users, we propose Sequential Topic Patterns (STPs) and formulate the problem of mining User-aware Rare Sequential Topic Patterns (URSTPs) in document streams on the Internet. They are rare on the whole but relatively frequent for specific users, so can be applied in many real-life scenarios, such as real-time monitoring on abnormal user behaviors. We present a group of algorithms to solve this innovative mining problem through three phases: preprocessing to extract probabilistic topics and identify sessions for different users, generating all the STP candidates with (expected) support values for each user by pattern-growth, and selecting URSTPs by making user-aware rarity analysis on derived STPs. Experiments on both real (Twitter) and synthetic datasets show that our approach can indeed discover special users and interpretable URSTPs effectively and efficiently, which significantly reflect users' characteristics.

Plain text documents created and distributed on the Internet are ever changing in various forms. Mining topics of these documents has significant applications in many domains. Most of the literature is devoted to topic modeling, while sequential patterns of topics in document streams are ignored. Moreover, traditional sequential pattern mining algorithms mainly focused on frequent patterns for deterministic data sets, and thus not suitable for document streams with topic uncertainty and rare patterns. In this paper, we formulate and handle the mining problem of rare Sequential Topic Patterns (STPs) for Internet document streams, which are rare on the whole but relatively often for specific users, so also interesting. Since this type of rare STPs reflects users’ specific behaviors, our work can be applied in many fields, such as personalized context-aware recommendation and real-time monitoring on abnormal user behaviors on the Internet. We propose a novel approach to discovering user-related rare STPs based on the temporal and probabilistic information of concerned topics. After extracting topics from documents by LDA and sorting the document stream into sessions for different users during different time periods, the proposed algorithms discover rare STPs by (1) mining STP candidates for each user through an efficient algorithm based on pattern-growth, and (2) generating user-related rare STPs by pattern rarity analysis. Experiments on both synthetic and real data sets show that our approach can discover interesting rare STPs very effectively and efficiently.

Semi-Markov conditional random fields (semi-CRFs) are usually trained with maximum a posteriori (MAP) criterion which adopts the 0/1 cost for measuring the loss of misclassification. In this paper, based on our previous work on handwritten Chinese/Japanese text recognition (HCTR) using semi-CRFs, we propose an alternative parameter learning method by minimizing the risk, in which the misclassification costs are not equal, but different depending on the hypothesis and the ground-truth. The proposed method is lattice-based, i.e., the hypothesis space is the entire lattice on which the semi-CRF is defined. Experimental results on two online handwriting databases: CASIA-OLHWDB and TUAT Kondate demonstrate that minimum-risk training can yield superior string recognition rates compared to MAP training.

Concept maps are an important tool to organize, represent, and share knowledge. Building a concept map involves creating text-based concepts and specifying their relationships with line-based links. Current concept map tools usually impose specific task structures for text and link construction, and may increase cognitive burden to generate and interact with concept maps. While pen-based devices (e.g., tablet PCs) offer users more freedom in drawing concept maps with a pen or stylus more naturally, the support for hand-drawn concept map creation and manipulation is still limited, largely due to the lack of methods to recognize the components and structures of hand-drawn concept maps. This article proposes a method to understand hand-drawn concept maps. Our algorithm can extract node blocks, or concept blocks, and link blocks of a hand-drawn concept map by combining dynamic programming and graph partitioning, recognize the text content of each concept node, and build a concept-map structure by relating concepts and links. We also design an algorithm for concept map retrieval based on hand-drawn queries. With our algorithms, we introduce structure-based intelligent manipulation techniques and ink-based retrieval techniques to support the management and modification of hand-drawn concept maps. Results from our evaluation study show high structure recognition accuracy in real time of our method, and good usability of intelligent manipulation and retrieval techniques.

Mining frequent itemsets over online data streams, where the new data arrive and the old data will be removed with high speed, is a challenge for the computational complexity. Existing approximate mining algorithms suffer from explosive computational complexity when decreasing the error parameter, isin, which is used to control the mining accuracy. We propose a new approximate mining algorithm using an approximate frequent itemset tree (abbreviated as AFI-tree), called AFI algorithm, to mine approximate frequent itemsets over online data streams. The AFI-tree based on prefix tree maintains only frequent itemsets, so the number of nodes in the tree is very small. All the infrequent child nodes of any frequent node are pruned and the maximal support of the pruned nodes is estimated to detect new frequent itemsets. In order to guarantee the mining accuracy, when the estimated maximal support of the pruned nodes is a bit more than the minimum support, their supports will be re-computed and the frequent nodes among them will be inserted into the AFI-tree. Experimental results show that the AFI algorithm consumes much less memory space than existing algorithms, and runs much faster than existing algorithms in most occasions.