Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate diverse yet interconnected data modalities—such as time series, system logs, and tabular records—as exemplified by modern IT systems. Effective AD methods in such environments must therefore possess two critical capabilities: (1) the ability to handle heterogeneous data formats within a unified framework, allowing the model to process and detect multiple modalities in a consistent manner during anomalous events; (2) a strong generalization ability to quickly adapt to new scenarios without extensive retraining. However, most existing methods fall short of these requirements, as they typically focus on single modalities and lack the flexibility to generalize across domains. To address this gap, we introduce a novel paradigm: In-Context Anomaly Detection (ICAD), where anomalies are defined by their dissimilarity to a relevant reference set of normal samples. Under this paradigm, we propose ICAD-LLM, a unified AD framework leveraging Large Language Models' in-context learning abilities to process heterogeneous data within a single model. Extensive experiments demonstrate that ICAD-LLM achieves competitive performance with task-specific AD methods and exhibits strong generalization to previously unseen tasks, which substantially reduces deployment costs and enables rapid adaptation to new environments. To the best of our knowledge, ICAD-LLM is the first model capable of handling anomaly detection tasks across diverse domains and modalities.

Knowledge compilation transforms logical theories into circuit representations that support efficient reasoning. We study this problem for propositional groundings of FO², the two-variable fragment of first-order logic over finite domains. Given an FO² sentence and a domain of size n, its grounding yields a propositional theory over ground atoms. We ask whether such theories admit compact representations in DNNF-based and related knowledge compilation languages, and whether these can be constructed efficiently, both with respect to the domain size n for a fixed sentence. We show first that compact compilation is impossible in general: there exists an FO² sentence whose grounding over a domain of size n requires DNNF size 2^Ω(n). On the positive side, we develop a two-stage compiler that exploits the symmetries inherent in the propositional groundings of FO² sentences. It branches on unary and binary types rather than individual ground atoms, in a similar spirit to lifted inferences for probabilistic relational models. Moreover, it optimizes the compilation process by efficiently identifying and caching residual subproblems that are equivalent with respect to future extensions. Experiments show the practical efficiency of our approach, which often produces smaller circuits and compiles faster than straightforward grounding-based baselines.

Aspect-based Sentiment Analysis (ABSA) evaluates sentiments toward specific aspects of entities within the text. However, attention mechanisms and neural network models struggle with syntactic constraints. The quadratic complexity of attention mechanisms also limits their adoption for capturing long-range dependencies between aspect and opinion words in ABSA. This complexity can lead to the misinterpretation of irrelevant contextual words, restricting their effectiveness to short-range dependencies. To address the above problem, we present a novel approach to enhance long-range dependencies between aspect and opinion words in ABSA (MambaForGCN). This approach incorporates syntax-based Graph Convolutional Network (SynGCN) and MambaFormer (Mamba-Transformer) modules to encode input with dependency relations and semantic information. The Multihead Attention (MHA) and Selective State Space model (Mamba) blocks in the MambaFormer module serve as channels to enhance the model with short and long-range dependencies between aspect and opinion words. We also introduce the Kolmogorov-Arnold Networks (KANs) gated fusion, an adaptive feature representation system that integrates SynGCN and MambaFormer and captures non-linear, complex dependencies. Experimental results on three benchmark datasets demonstrate MambaForGCN’s effectiveness, outperforming state-of-the-art (SOTA) baseline models.

We study the model enumeration problem of the function-free, finite domain fragment of first-order logic with two variables (FO2). Specifically, given an FO2sentence Γ and a positive integer n, how can one enumerate all the models of Γ over a domain of size n? In this paper, we devise a novel algorithm to address this problem. The delay complexity, the time required between producing two consecutive models, of our algorithm is quadratic in the given domain size n (up to logarithmic factors) when the sentence is fixed. This complexity is almost optimal since the interpretation of binary predicates in any model requires at least Ω(n2) bits to represent.

In recent years, graph neural networks (GNNs) have emerged as a promising approach for classifying non-Euclidean structural data. However, the practical implementation of GNNs faces challenges related to their limited scalability due to the presence of multi-hop data dependencies. In order to tackle this issue, existing methods have employed teacher GNNs to generate labels, which are then used to train multilayer perceptrons (MLPs) based solely on node features, without considering any structural information. However, these methods primarily focus on the soft labels generated by the teacher GNNs, leading to suboptimal performance because they disregard significant features of the teacher GNNs. Additionally, since the structural information of the graph is omitted in the input of MLPs, it can be more susceptible to the influence of erroneous features. To address these limitations, this paper proposes a novel framework that incorporates a new distillation strategy to integrate soft feature similarity into MLPs, while also utilizing contrastive learning to enhance the training of student MLPs. Our model has accuracy, averaged over seven public datasets, 5.21% higher than state-of-the-art (SOTA) methods, and even 2.49% higher than teacher GNNs over five standard scaled datasets. At the same time, its inference time is only 1.17% of comparable GNNs.

Personalized exercise recommendation is an important task in educational data mining, aiming to recommend exercises that match students’ intentions and abilities. However, existing recommendation methods often ignore the dynamic changes and individual differences in students’ knowledge levels and face serious data sparsity problems. To address these limitations, we employ graph neural networks (GNNs) to learn node representations in exercise recommendation contexts and propose a new knowledge tracing-enhanced multitask exercise recommendation framework, called MLKT4Rec. Unlike previous graph-based approaches that focus on explicitly observed relationships in the data, we use implicit edges to augment the graph structure and incorporate exercise difficulty attributes, relative time intervals, and location coding to enrich the exercise representation. Based on this, we construct a knowledge tracing model to capture students’ knowledge levels and integrate it into the exercise sequential recommendation process for joint multitask training. Extensive experiments on four real datasets validate the effectiveness of the proposed model.

In this paper, we study the sampling problem for first-order logic proposed recently by Wang et al.—how to efficiently sample a model of a given first-order sentence on a finite domain? We extend their result for the universally-quantified subfragment of two-variable logic FO2(UFO2) to the entire fragment of FO2. Specifically, we prove the domain-liftability under sampling of FO2, meaning that there exists a sampling algorithm for FO2that runs in time polynomial in the domain size. We then further show that this result continues to hold even in the presence of counting constraints, such as ∀x∃=ky : φ(x, y) and ∃=kx∀y : φ(x, y), for some quantifier-free formula φ(x, y). Our proposed method is constructive, and the resulting sampling algorithms have potential applications in various areas, including the uniform generation of combinatorial structures and sampling in statistical-relational models such as Markov logic networks and probabilistic logic programs.

The advance in single-cell RNA-sequencing (scRNA-seq) sheds light on cell-specific transcriptomic studies of cell developments, complex diseases and cancers. Nevertheless, scRNA-seq techniques suffer from 'dropout' events, and imputation tools are proposed to address the sparsity. Here, rather than imputation, we propose a tool, SMURF, to extract the low-dimensional embeddings from cells and genes utilizing matrix factorization with a mixture of Poisson-Gamma divergent as objective while preserving self-consistency. SMURF exhibits feasible cell subpopulation discovery efficacy with obtained cell embeddings on replicated in silico and eight web lab scRNA datasets with ground truth cell types. Furthermore, SMURF can reduce the cell embedding to a 1D-oval space to recover the time course of cell cycle. SMURF can also serve as an imputation tool; the in silico data assessment shows that SMURF parades the most robust gene expression recovery power with low root mean square error and high Pearson correlation. Moreover, SMURF recovers the gene distribution for the WM989 Drop-seq data. SMURF is available at https://github.com/deepomicslab/SMURF.

We study the problem of constructing the relational marginal polytope (RMP) of a given set of first-order formulas. Past work has shown that the RMP construction problem can be reduced to weighted first-order model counting (WFOMC). However, existing reductions in the literature are intractable in practice, since they typically require an infeasibly large number of calls to a WFOMC oracle. In this paper, we propose an algorithm to construct RMPs using fewer oracle calls. As an application, we also show how to apply this new algorithm to improve an existing approximation scheme for WFOMC. We demonstrate the efficiency of the proposed approaches experimentally, and find that our method provides speed-ups over the baseline for RMP construction of a full order of magnitude.

With the frequent occurrence of unconventional global emergencies, the public security field has received more and more attention. As an unconventional emergency, terrorist attacks have aroused global attention. So, how should we extract useful information from a large number of terrorist attacks and find the law of the attack, so that we can effectively prevent or take early measures to reduce losses? To this end, we are based on the Global Terrorism Database (GTD), and aim to predict the next province or state a terrorist organization may attack at a specific time point by mining the terrorist organizations' historical records and other types of information availabl, such as incident information and so on. Then, Based on these incident information and spatiotemporal information, we propose a neural network called ATtention-based Fused-SpatialTemporal LSTM (ATFST-LSTM) to predict the next location which may be attacked. We test the efficiency of our models on GTD, experiments show that our models has achieved better results.

In this paper, we study the problem of recommending the appropriate datasets for authors, which is implemented to infer the proximity between authors and datasets by leveraging the information from a three-layered network, composed by authors, papers and datasets. To link author-dataset semantically by taking advantage of the rich content information of papers in the intermediate layer, we design an attentive and aggregate multi-layer network learning model. The aggregation is for integrating the intra-layer information of paper content and citations, while the attention is used for coordinating authors at the top-layer and datasets at the bottom-layer in the semantic space learned from papers in the intermediate layer. The experimental study demonstrates the superiority of our method compared with the solutions that extend existing models to our problem.

A metropolis consists of zones segmented by major roads. People travel between zones to conduct social activities. To analyze the characteristics of the entire city, we can explore regions' features and find region-wise latent relationships. In this paper, we propose a semantic associated zone embedding (SAZE) method using distributed representation learning. SAZE can generate zone embeddings which extract more comprehensive characteristics of each zone and fit for many urban computing tasks, rather than the task-oriented methods. To feed our SAZE, we not only consider the connections between zones via trajectory, but also embed its intrinsic properties. Furthermore, we apply SAZE to two tasks, zone classification and zone clustering visualization, respectively. For each task, we compare SAZE with other state-of-the-art baseline methods and the results have demonstrated the advantage of our model over the several methods.

Network embedding, also known as graph representation, is a classical topic in data mining. It has been widely used in real-world network applications such as node classification and community detection. However, it remains open to find a method that is scalable and preserves both structure and content information. Based on generative adversarial networks, we propose an unsupervised network embedding framework NEGAN, which is featured by combining graph topology and node content. In NEGAN, network nodes are mapped to the target space in a highly flexible non-linear way, guided by the content of the nodes. This mapping is learned from the generator of the generative adversarial networks, and node adjacency in the input network is preserved. Experiments on real datasets show that NEGAN outperforms all the existing methods on many scenarios including node classification, visualization and community detection tasks.

In vehicular ad hoc networks, vehicular nodes take the responsibility of data collection and exchange for smart transportation services. When an emergency occurs, such as traffic accident, how to propagate the alert message to relevant vehicles efficiently and quickly, is still an open problem. In this paper, a neighbor-decoding-based data propagation scheme is proposed, called NED. It utilizes network coding to improve the quality of data transmissions. Considering the options among raw blocks and encoded blocks, the sender selects the one to send, which has the highest decoding capability of neighbors. This selection guarantees a relatively large number of decoded blocks at neighbors after they receive this block. Experiments using real trajectory data show that NED has a high block decoding rate and a high packet coverage rate while keeping similar dissemination delay.

Borgs et al. [2016] investigated essential requirements for communities in preference networks. They defined six axioms on community functions, i.e., community detection rules. Though having elegant properties, the practicality of this axiomsystem is compromised by the intractability of checking twocritical axioms, so no nontrivial consistent community functionwas reported in [Borgs et al., 2016]. By adapting the two axioms in a natural way, we propose two new axioms that are efficiently-checkable. We show that most of the desirable properties of the original axiom system are preserved. More importantly, the new axioms provide a general approach to constructing consistent community functions. We further find a natural consistent community function that is also enumerable and samplable, answering an open problem in the literature.

In vehicular networks, since reliable end-to-end paths between data source and destination seldom exist, replication-based routing protocols are widely used to increase the delivery ratio and reduce the transfer delay. However, after a data message is delivered, its replicas still exist and greatly waste network resources, such as transmission bandwidth and storage spaces. In mobile multimedia communications, the large size of multimedia data greatly aggravates this situation. In this paper, we propose a GPS-based replica deletion scheme with anti-packet distribution for vehicular networks, namely RAD. It utilizes vehicle-to-vehicle and vehicle-to-roadside-unit communications to remove redundant data replicas by a certain number of anti-packets. A roadside unit at each crossing distributes its collected anti-packets to nearby vehicles moving for different directions according to the geographical locations of the to-be-deleted targets. This distribution increases the delivery probability of these anti-packets. Experiment results in a real taxi network show that, compared with others, RAD accelerates replica deletion with less extra overhead

In this paper, we study the block delivery delay of random linear network coding in two-hop single-unicast delay-tolerant networks with grid-based mobility. By block delivery delay, we mean how long it takes the destination to receive all the K information packets of a single block. Our work includes two parts. First, we give a general analysis of the dependency between packet spaces spanned by different nodes in a stochastic way. Then we simplify the result by means of the approximation. By the dependency analysis, we can accurately update nodes' innovativeness rank. Second, via tracking the innovativeness ranks of all nodes, we develop an analytic framework to iteratively compute the cumulative distribution function of the block delivery delay. Our simulation results verify that both parts of our analysis are sufficiently accurate. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract Wireless sensor networks are prone to failure, so prolonging their lifetime and preventing loss of connectivity are significant. A simple but efficient strategy is to place redundant sensor nodes to establish multi‐connectivity. This paper explores how to add as few as possible nodes (called Steiner nodes) to a sensor network such that the resulting network isk‐connected or partiallyk‐connected.k‐connectivity means that each pair of the nodes, whether Steiner or original, is connected by at leastknode‐disjoint paths, while partialk‐connectivity only requires such connectivity among original nodes. The contribution lies in two aspects. First, the approximation ratio of an existingk‐connectivity repair algorithm is decreased fromO(k4α) toO(k3α), whereαis the approximation ratio of any algorithm that finds a minimum‐weightk‐connected spanning subgraph of a weighted complete graph. This is the best result ever obtained. Second, the first generic partialk‐connectivity repair algorithm is proposed. It is proved that the approximation ratio of this algorithm is at mostO(k3α). Copyright © 2008 John Wiley & Sons, Ltd.

There has been a growing interest in wireless sensor networks (WSNs). Considering the limited energy, memory and computational capacity of the sensor nodes, it becomes necessary to ensure rational use of their resources. The fairness and congestion control are also need to be taken into account. It is in this context that a robust routing algorithm with fair congestion control in wireless sensor network (called RRA- FCC) is proposed. RRA-FCC performs a low cost and robust routing based on dividing the monitoring region into several subareas initially. Furthermore, RRA-FCC provides a fair congestion control, which improves the whole network fairness in congestion. The simulation results show that RRA-FCC performs well in the throughput of Sink nodes, energy consumption and the whole network fairness in congestion.