Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning. However, existing studies on the expressive power of GNNs mainly focuses on simple single-relation graphs, and there is still insufficient discussion on the power of GNN to express logical rules in KGs. How to enhance the logical expressive power of GNNs is still a key issue. Motivated by this, we propose Path-Neighbor enhanced GNN (PN-GNN), a method to enhance the logical expressive power of GNN by aggregating node-neighbor embeddings on the reasoning path. First, we analyze the logical expressive power of existing GNN-based methods and point out the shortcomings of the expressive power of these methods. Then, we theoretically investigate the logical expressive power of PN-GNN, showing that it not only has strictly stronger expressive power than C-GNN but also that its (k+1)-hop logical expressiveness is strictly superior to that of k-hop. Finally, we evaluate the logical expressive power of PN-GNN on six synthetic datasets and two real-world datasets. Both theoretical analysis and extensive experiments confirm that PN-GNN enhances the expressive power of logical rules without compromising generalization, as evidenced by its competitive performance in KG reasoning tasks.

Unmanned aerial vehicle (UAV) communications are susceptible to malicious compound interference signals due to the complexity and variability of the electromagnetic environment and the openness of the air-to-ground wireless channels, leading to degradation of communication quality. Therefore, effective detection and accurate recognition of compound interference are the key to ensuring secure UAV communication in complex environments. However, existing deep learning-based interference recognition algorithms suffer from fewer recognizable compound interference types, a large number of model parameters, and lower interference recognition accuracy under low interference-to-noise power ratio (INR) conditions. This paper proposes a malicious compound interference recognition method for UAV communication based on multi-modal multi-label learning and designs a lightweight multi-modal interference recognition network. By introducing a multi-label learning mechanism and making full use of the complementary information between different modalities of the signal, the method can achieve more flexible, accurate and stable recognition of compound interference signals under low INR. We construct both simulation and real measured datasets containing 31 classes of compound interference signals, and conduct simulation experiments with sufficient samples, insufficient samples, and different training strategies. The results demonstrate that the proposed method enhances the recognition accuracy of UAV communication compound interference under low INR and across different training datasets, all while maintaining a small number of model parameters.

Among various temporal knowledge graph (TKG) extrapolation methods, rule-based approaches stand out for their explicit rules and transparent reasoning paths. However, the vast search space for rule extraction poses a challenge in identifying high-quality logic rules. To navigate this challenge, we explore the use of generation models to generate new rules, thereby enriching our rule base and enhancing our reasoning capabilities. In this paper, we introduce LLM-DR, an innovative rule-based method for TKG extrapolation, which harnesses diffusion models to generate rules that are consistent with the distribution of the source data, while also amalgamating the rich semantic insights of Large Language Models (LLMs). Specifically, our LLM-DR generates semantically relevant and high-quality rules, employing conditional diffusion models in a classifier-free guidance fashion and refining them with LLM-based constraints. To assess rule efficacy, we meticulously design a coarse-to-fine evaluation strategy that initiates with coarse-grained filtering to eliminate less plausible rules and proceeds with fine-grained scoring to quantify the reliability of the retained. Extensive experiments demonstrate the promising capacity of our LLM-DR.

Nodes in the real-world graphs exhibit diverse patterns in numerous aspects, such as degree and homophily. However, most existent node predictors fail to capture a wide range of node patterns or to make predictions based on distinct node patterns, resulting in unsatisfactory classification performance. In this paper, we reveal that different node predictors are good at handling nodes with specific patterns and only apply one node predictor uniformly could lead to suboptimal result. To mitigate this gap, we propose a mixture of experts framework, MoE-NP, for node classification. Specifically, MoE-NP combines a mixture of node predictors and strategically selects models based on node patterns. Experimental results from a range of real-world datasets demonstrate significant performance improvements from MoE-NP.

Achieving high-precision interference recognition for autonomous aerial vehicle (AAV) swarm communications in complex electromagnetic environments is of great significance for developing efficient anti-interference schemes and improving the security of AAV swarm communication. Although deep learning-based interference recognition methods for AAV swarm communication can achieve good recognition performance, they usually rely on a large number of high-quality labeled samples and only consider a single representation of the interference signal as input. This leads to low accuracy and poor robustness of interference recognition in scenarios with changing electromagnetic environments or insufficient samples. To address these issues, this article proposes a data-knowledge-driven method for AAV swarm communication interference recognition. A dual-input interference recognition network (DIRNet) with a few model parameters is designed, incorporating deep features extracted based on the data-driven approach and manual features designed based on expert knowledge. Simulation experiments are conducted under sufficient-sample, cross-environment, and insufficient-sample scenarios. The results demonstrate that the proposed AAV swarm communication interference recognition method not only improves the recognition accuracy of interference signals under these conditions. Moreover, it also shows good robustness in complex dynamic environments.

Automatic modulation recognition plays a crucial role in the domain of electromagnetic situational awareness. Early recognition methods predominantly relied on expert experience and prior knowledge, demanding a high level of professional background and experience from practitioners, and usually underperformed in complex signal environments. In recent years, the continual development of deep learning (DL) technologies has introduced solution ideas to address the challenge of modulation recognition in complex electromagnetic environments. However, DL methods heavily depend on large volumes of high-quality labeled data and face challenges in real electromagnetic environments with limited samples. To fully leverage the respective strengths of expert knowledge in the radio domain and data-driven approaches, this article proposes a hybrid-driven neural network (HDNet) framework for radio signal recognition. HDNet integrates deep features extracted through data-driven methods with manual features extracted based on expert knowledge, aiming to enhance recognition performance in few-shot scenarios. Experimental results on both simulated and real measured datasets demonstrate that HDNet achieves high-recognition accuracy and robustness.

Large models require larger datasets. While people gain from using massive amounts of data to train large models, they must be concerned about privacy issues. To address this issue, we propose a novel approach for private generative modeling using the Sliced Wasserstein Distance (SWD) metric in a Differential Private (DP) manner. We propose Normalized Clipping, a parameter-free clipping technique that generates higher-quality images. We demonstrate the advantages of Normalized Clipping over the traditional clipping method in parameter tuning and model performance through experiments. Moreover, experimental results indicate that our model outperforms previous methods in differentially private image generation tasks.

Temporal knowledge graph (TKG) reasoning has two settings: interpolation reasoning and extrapolation reasoning.Both of them draw plenty of research interest and have great significance.Methods of the former deemphasize the temporal correlations among facts sequences, while methods of the latter require strict chronological order of knowledge and ignore inferring clues provided by missing facts of the past.These limit the practicability of TKG applications as almost all of the existing TKG reasoning methods are designed specifically to address either one setting.To this end, this paper proposes an original Temporal PAth-based Reasoning (TPAR) model for both the interpolation and extrapolation reasoning.TPAR performs a neural-driven symbolic reasoning fashion that is robust to ambiguous and noisy temporal data and with fine interpretability as well.Comprehensive experiments show that TPAR outperforms SOTA methods on the link prediction task for both the interpolation and the extrapolation settings.A novel pipeline experimental setting is designed to evaluate the performances of SOTA combinations and the proposed TPAR towards interpolation and extrapolation reasoning.More diverse experiments are conducted to show the robustness and interpretability of TPAR.

Temporal factors are tied to the growth of facts in realistic applications, such as the progress of diseases and the development of political situation, therefore, research on Temporal Knowledge Graph (TKG) attracks much attention.In TKG, relation patterns inherent with temporality are required to be studied for representation learning and reasoning across temporal facts.However, existing methods can hardly model temporal relation patterns, nor can capture the intrinsic connections between relations when evolving over time, lacking of interpretability.In this paper, we propose a novel temporal modeling method which represents temporal entities as Rotations in Quaternion Vector Space (RotateQVS) and relations as complex vectors in Hamilton's quaternion space.We demonstrate our method can model key patterns of relations in TKG, such as symmetry, asymmetry, inverse, and can further capture time-evolved relations by theory.Empirically, we show that our method can boost the performance of link prediction tasks over four temporal knowledge graph benchmarks.

In the last few years, the availability of temporal knowledge graphs has stimulated extensive research in temporal knowledge graph completion (TKGC) and temporal knowledge graph embedding (TKGE), where temporal information is added to static knowledge graphs that have been widely applied previously. However, most existing methods, such as current state-of-the-art DE-SimplE and TeRo, learn embeddings of temporal-evolving attributes, overlooking the inherent attributes inside entities, where some essential and inherent features are included. In this paper, we introduce a novel method utilizing Inherent Attributes with a Graph Attention network (IAGAT) for TKGC. Our IAGAT extracts inherent attributes from sufficient features corresponding to various facts at different time stamps, to obtain the inherent embeddings. And we take advantages of previous rotation based methods to obtain the temporal-evolving embed-dings. Through extensive experiments and sufficient comparisons, we demonstrate our model outperforms the current state-of-the-art models on link prediction task. Furthermore, we evaluate and prove the necessity of the inherent attributes in performance improvement, and study how our model functions in extracting inherent features.

Knowledge Graphs represent facts with triples containing head entity$h$, tail entity$t$and relation$r$which facilitate applications of many scenarios, for example intelligent web search, community detection and question answering. Knowledge Graph Embedding (KGE) represents elements of triples in a low-dimensional continuous vector space. Though it has been widely studied by both academic and industry communities, most researches focus on learning embeddings of entities and relations separately rather than considering the interactive semantic information between them. However, neither relations nor entities exist lonely out of context. In this paper, we define an interactive semantic space to model the context of triples and propose a novel Bi-linear Semantic Matching Method using Convolutional networks (BiSC). Specifically, we use 1D convolutional neural networks to extract features of the interactive semantics and then compute the similarity scores in the bi-linear space. Compared to existing complex graph network methods, BiSC needs lower computational cost to reach competitive results on link prediction task. The consistent state-of-the-art performance through extensive experiments over two benchmarks demonstrates the advantages of the proposed BiSC model. Further analysis on convergence study and case study of interactive semantic space show the efficiency of our model.

Credit card fraud detection (CCFD) is important for protecting the cardholder’s property and the reputation of banks. Class imbalance in credit card transaction data is a primary factor affecting the classification performance of current detection models. However, prior approaches are aimed at improving the prediction accuracy of the minority class samples (fraudulent transactions), but this usually leads to a significant drop in the model’s predictive performance for the majority class samples (legal transactions), which greatly increases the investigation cost for banks. In this paper, we propose a heterogeneous ensemble learning model based on data distribution (HELMDD) to deal with imbalanced data in CCFD. We validate the effectiveness of HELMDD on two real credit card datasets. The experimental results demonstrate that compared with current state‐of‐the‐art models, HELMDD has the best comprehensive performance. HELMDD not only achieves good recall rates for both the minority class and the majority class but also increases the savings rate for banks to 0.8623 and 0.6696, respectively.

The Multi-choice machine reading comprehension, selecting the correct answer in the candidate answers, requires obtaining the interaction semantics between the given passage and the question. In this paper, we propose an end-to-end deep learning model. It employs Bi-GRU to contextually encode passages and question, and specifically models complex interactions between the given passage and the question by six kinds of attention functions, including the concatenated attention, the bilinear attention, the element-wise dot attention, minus attention and bi-directional attentions of Query2Context, Context2Query. Then, we use the multi-level attention transfer reasoning mechanism to focus on further obtaining more accurate comprehensive semantics. To demonstrate the validity of our model, we performed experiments on the large reading comprehension data set RACE. The experimental results show that our model surpasses many state-of-the-art systems on the RACE data set and has good reasoning ability.

Abstract Multi-source knowledge fusion is one of the important research topics in the fields of artificial intelligence, natural language processing, and so on. The research results of multi-source knowledge fusion can help computer to better understand human intelligence, human language and human thinking, effectively promote the Big Search in Cyberspace, effectively promote the construction of domain knowledge graphs (KGs), and bring enormous social and economic benefits. Due to the uncertainty of knowledge acquisition, the reliability and confidence of KG based on entity recognition and relationship extraction technology need to be evaluated. On the one hand, the process of multi-source knowledge reasoning can detect conflicts and provide help for knowledge evaluation and verification; on the other hand, the new knowledge acquired by knowledge reasoning is also uncertain and needs to be evaluated and verified. Collaborative reasoning of multi-source knowledge includes not only inferring new knowledge from multi-source knowledge, but also conflict detection, i.e. identifying erroneous knowledge or conflicts between knowledges. Starting from several related concepts of multi-source knowledge fusion, this paper comprehensively introduces the latest research progress of open-source knowledge fusion, multi-knowledge graphs fusion, information fusion within KGs, multi-modal knowledge fusion and multi-source knowledge collaborative reasoning. On this basis, the challenges and future research directions of multi-source knowledge fusion in a large-scale knowledge base environment are discussed.

One of the key challenges for question answering is to bridge the lexical gap between questions and answers because there may not be any matching word between them. Machine translation models have been shown to boost the performance of solving the lexical gap problem between question-answer pairs. In this paper, we introduce an attention-based deep learning model to address the answer selection task for question answering. The proposed model employs a bidirectional long short-term memory (LSTM) encoder-decoder, which has been demonstrated to be effective on machine translation tasks to bridge the lexical gap between questions and answers. Our model also uses a step attention mechanism which allows the question to focus on a certain part of the candidate answer. Finally, we evaluate our model using a benchmark dataset and the results show that our approach outperforms the existing approaches. Integrating our model significantly improves the performance of our question answering system in the TREC 2015 LiveQA task.

With the rapid development of big data analytics, mobile computing, Internet of Things, cloud computing, and social networking, cyberspace has expanded to a cross-fused and ubiquitous space made up of human beings, things, and information. Internet applications have evolved from Web 1.0 to Web 2.0 and Web 3.0, and web information has seen an explosive growth, which is strongly promoting the advent of a global era of big data. In this ubiquitous cyberspace, traditional search engines can no longer fully satisfy the evolving needs of various types of users. Therefore, search engines must make completely innovative, revolutionary changes for the next generation of search, which is referred to as “big search”. This paper first studies the development needs of big search. Then, big search is defined, and the 5S properties (Sourcing, Sensing, Synthesizing, Solution, and Security) of big search, which are different from those of traditional search engines, are elaborated. Also, the paper provides a system architecture for big search, explores the key technologies that support the 5S properties, and describes potential application fields of big search technology. Finally, the research opportunities of big search are discussed.

Social networks have been part of people's daily life and plenty of users have registered accounts in multiple social networks. Interconnections among multiple social networks add a multiplier effect to social applications when fully used. With the sharp expansion of network size, traditional standalone algorithms can no longer support computing on large scale networks while alternatively, distributed and parallel computing become a solution to utilize the data-intensive information hidden in multiple social networks. As such, synergistic partitioning, which takes the relationships among different networks into consideration and focuses on partitioning the same nodes of different networks into same partitions. With that, the partitions containing the same nodes can be assigned to the same server to improve the data locality and reduce communication overhead among servers, which are very important for distributed applications. To date, there have been limited studies on multiple large scale network partitioning due to three major challenges: 1) the need to consider relationships across multiple networks given the existence of intricate interactions, 2) the difficulty for standalone programs to utilize traditional partitioning methods, 3) the fact that to generate balanced partitions is NP-complete. In this paper, we propose a novel framework to partition multiple social networks synergistically. In particular, we apply a distributed multilevel k-way partitioning method to divide the first network into k partitions. Based on the given anchor nodes which exist in all the social networks and the partition results of the first network, using MapReduce, we then develop a modified distributed multilevel partitioning method to divide other networks. Extensive experiments on two real data sets demonstrate that our method can significantly outperform baseline independent-partitioning method in accuracy and scalability.

For the high machining precision and various complicated constraints, process planning of cylinder block always receives lots of attention from industry and academic fields. FMEs (feature machining elements, FMEs) is proposed in this paper, which subdivided from design features and had a close correlation with machining methods according to machining accuracies and manufacturing resources. Therefore, the problem of process planning could be represented by an optimal sequencing and balancing of those FMEs. After analysis of constraints of features and FMEs, an optimal objective is established during a certain stage, and a process planning is generated and optimized by using an improved genetic simulated annealing algorithm (GSA). Finally, a case of cylinder block reveals that the proposed method is feasible and efficient.

In this paper, we tackle a novel problem of ranking multivalued objects, where an object has multiple instances in a multidimensional space, and the number of instances per object is not fixed. Given an ad hoc scoring function that assigns a score to a multidimensional instance, we want to rank a set of multivalued objects. Different from the existing models of ranking uncertain and probabilistic data, which model an object as a random variable and the instances of an object are assumed exclusive, we have to capture the coexistence of instances here. To tackle the problem, we advocate the semantics of favoring widely preferred objects instead of majority votes, which is widely used in many elections and competitions. Technically, we borrow the idea from Borda Count (BC), a well-recognized method in consensus-based voting systems. However, Borda Count cannot handle multivalued objects of inconsistent cardinality, and is costly to evaluate top (k) queries on large multidimensional data sets. To address the challenges, we extend and generalize Borda Count to quantile-based Borda Count, and develop efficient computational methods with comprehensive cost analysis. We present case studies on real data sets to demonstrate the effectiveness of the generalized Borda Count ranking, and use synthetic and real data sets to verify the efficiency of our computational method.

The problem of communication reduction over continuous threshold monitoring in distributed systems is considered in this paper. A Communication Efficient Method (CEM) is proposed which utilizes the relationship among objects and processes them as a whole, therefore achieves better performance than those who holding each object separately. In specific, the object with largest value is chose as the representative object, and adjustment factors are used to guarantee that local value of representative object is also the largest one in each remote node. Therefore, only the representative object needs to be monitored continuously as long as all the local constraints are valid. When local constraint is violated, communication is needed among the coordinator and remote nodes to rebuild the constraint. The algorithms are described in this paper; algorithms' correctness proof and extension are also provided. Experimental evaluation on real data sets show the efficiency of CEM on communication reduction over distributed threshold monitoring.

We address the problem of cost-efficient processing of continuous extreme queries (MAX or MIN) over distributed sliding window streams, and propose several methods for communication reduction and resource sharing among queries. Firstly, we develop an effective pruning technique to minimize the number of elements to be kept. It can be shown that on average only O(logN) key points need to be stored for exact answer of extreme query, where N is the number of points contained in the sliding window. Then we consider the distributed environment, where remote nodes delay the data transmission as late as possible, and adopt the pruning strategy to filter local stream tuples, which is quite efficient in communication reduction. An efficient algorithm called MCEQP is proposed in the coordinator node for continuously monitoring K queries with different sliding window widths, and the linklist-implemented instance of MCEQP can update all K results in O(M+K) time when a new tuple arrives, where M is the cardinality of key points set corresponding to the widest window. Theoretical analysis and experimental evidences show the efficiency of proposed approach both on storage/communication reduction and efficiency improvement.

Given a minimum threshold in a massive market-basket data set, an item pair whose correlation above the threshold is considered correlated. In this paper, we provide a randomized algorithm SERIT-a Searching-corrElated-pair Randomized algorithm for dIfferent Thresholds- to find all correlated pairs effectively, which adopts the Pearson's correlation coefficient [11] as the measure criterion. In their CIKM'06 paper [2], Zhang et al. address the same problem by taking the relation of Pearson's coefficient and Jaccard distance into account. However, it is inefficient when the threshold is small. We propose a new probability function to prune uncorrelated item pairs based on [2], which can cover the shortage of the former one. Experimental results with synthetic and real data sets reveal that with a given threshold, even if it is small, SERIT algorithm can prune the item pairs unwanted efficiently and save large computational resources.

Continuous top-k query over data stream is very important for several on-line applications, including network monitoring, communication, sensor networks and stock market trading, etc. In this paper, we propose an effective pruning technique, which minimizes the number of tuples that need to be stored and manipulated. Based on it, a cost-efficient method for continuous top-k processing over single data stream is proposed, whose computation complex and memory requirements are greatly decreased. The data structure we use is able to support preference function whether it is or not monotonic and the running time is hardly effected by dimensions. Theoretical analysis and experimental evidences show the efficiency of proposed approaches both on storage reduction and performance improvement.