Identification of influential groups of nodes in attributed graphs has applications in a wide range of real-world problems, for instance, collecting important proceedings in citation networks, or identifying essential genes for diagnosing disease in Protein-Protein Interaction networks. Previous approaches for influence maximization manipulated on the graph structure, despite their proliferation, neglect the node attribute information containing additional knowledge. In this work, we introduce Global Graph UNderstanding (GGUN), a perturbation-based framework leveraging the explanatory power of Graph Neural Networks. It takes into account the entire graph structure and node attributes simultaneously and fuses knowledge through GNN layers. Following the perturbation-based explanation, GGUN fills the gap between Deep Neural Network gradient-based feature importance analysis and discrete structure in the graph, which is formulated as a combinatorial optimization problem. Moreover, GGUN obtains an efficient solution by relaxing the infeasible combinatorial optimization problem with performance guaranteed. Evaluations of synthetic and real-world datasets show that GGUN outperforms baselines on both quantitative metrics and human-intelligible analysis.

Dynamic Dependence Network (DDN) inference is crucial for understanding evolving relationships in multimodal time series web data, with broad applications in fields like medical and financial network analysis. The inherent dynamic nature, temporal continuity, and heterogeneous data sources in multimodal time series data pose three fundamental challenges: computational efficiency, prediction stability and robustness, and modality quality disparity. Previous methods, generally lacking utilization of multiple modalities, either struggle with computational efficiency due to the time-intensive manual hyperparameter tuning, or compromise prediction stability and robustness by neglecting temporal coherence. To address these challenges, we propose a Normalized mutual information-driven Tuning-free Dynamic Dependence Network inference method for multimodal data, namely NoTeNet. NoTeNet provides a promising paradigm that can integrate two different data modalities to enhance prediction accuracy. It uses normalized mutual information transforms noisy auxiliary data into relationship matrices and employs a kernel function for smooth temporal estimation. Additionally, NoTeNet significantly reduces the need for manual hyperparameter adjustments, offering a tuning-free approach with theoretical guarantees. On various synthetic datasets and real-world data, NoTeNet demonstrates superior prediction accuracy and efficiency without the need for hyperparameter tuning, making it potential for a wide range of web data applications.

Covariance matrix estimation is an important problem in statistics, with wide applications in finance, neuroscience, meteorology, oceanography, and other fields. However, when the data are high-dimensional and constantly generated and updated in a streaming fashion, the covariance matrix estimation faces huge challenges, including the curse of dimensionality and limited memory space. The existing methods either assume sparsity, ignoring any possible common factor among the variables, or obtain poor performance in recovering the covariance matrix directly from sketched data. To address these issues, we propose a novel method - KEEF: Knowledge-based Time and Memory Efficient Covariance Estimator in Factor Model and its extended variation. Our method leverages historical data to train a knowledge-based sketch matrix, which is used to accelerate the factor analysis of streaming data and directly estimates the covariance matrix from the sketched data. We provide theoretical guarantees, showing the advantages of our method in terms of time and space complexity, as well as accuracy. We conduct extensive experiments on synthetic and real-world data, comparing KEEF with several state-of-the-art methods, demonstrating the superior performance of our method.

Human action recognition using commercial millimeter wave radar is gaining significant attention in smart elderly care and smart homes. Due to privacy concerns, the sensing data often needs to be processed locally on embedded systems with restricted computational resources, necessitating a balance between recognition accuracy and efficiency. In this paper, we propose a fast human action recognition framework based on 3D point cloud sequences generated by commercial 4D millimeter wave imaging radar systems. The framework comprises two primary phases: data preprocessing and spatial-temporal feature extraction. During the data preprocessing phase, we employ a sliding window approach for frame fusion to enhance the spatial information of the sparse point cloud while retaining its temporal features. Additionally, Morton coding is used to address the disorderliness in the point cloud sequence. For spatial-temporal feature extraction, we introduce an innovative two-stage algorithm. In the spatial feature extraction stage, we initially extract local spatial features for each point, utilizing self-attention to construct a local graph and circumvent the limitations of using Euclidean distance in sparse point clouds. Subsequently, 3D frame fusion convolution is applied to extract spatial features at the frame level, reducing the length of the spatial feature map sequence and lowering computational requirements for subsequent temporal feature extraction. In the temporal feature extraction stage, we employ a modified Transformer encoder with fine-grained feature fusion to extract temporal features. We conducted comprehensive experiments using both our collected dataset and the open dataset RadHar. The experimental outcomes demonstrate that our framework not only improves inference accuracy but also maintains satisfactory real-time performance on embedded platforms with constrained computational resources. When compared with state-of-the-art (SOTA) methods, our framework significantly enhances inference speed while retaining competitive inference accuracy. Codes and dataset are available at https://github.com/Feiyuyu0503/FastHAR.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by accessing external data sources, offering a promising way to improve accuracy and reliability. Despite its potential, conventional retrievers encounter bias and flaws with time-sensitive queries. In this paper, a benchmark query dataset is constructed to retrieve documents containing time-evolving facts, and the results show that current embedding-based similarity-matching methods struggle to handle queries with explicit temporal constraints. Therefore, we propose a novel approach that integrates supervised contrastive learning with tailored negative sample pairs for temporal constraints to train the retriever of an RAG system, along with query-side fine-tuning and routing techniques. Experimental results show that our approach significantly enhances the retriever performance of time-sensitive queries while ensuring the effectiveness of general queries. We will make the code and dataset publicly available at https://github.com/suzhou-22/TS-Retriever.

Accurately predicting Vehicle Energy Consumption (VEC) is crucial for estimating a vehicle's total energy requirements along a predetermined trajectory. Current research mainly focuses on personalized models that enhance VEC prediction accuracy by leveraging driving behavior features extracted from historical trajectory data. However, there are still two significant limitations. First, existing algorithms predominantly model trajectories with coarse granularity, focusing solely on overall characteristics and neglecting the crucial interplay between vehicles, drivers, and the environments, which fundamentally shape trajectory dynamics. Second, current models predict driver behavior preferences solely from vehicle operational states in historical trajectories, often overlooking the influence of external environmental factors. To overcome these limitations, we introduce a Spatial-Temporal Framework for Energy Consumption Prediction of Vehicle Trajectories (ST-ECP). Specifically, we construct a heterogeneous interaction graph that captures the complex relationships between vehicles, environments, and drivers, effectively characterizing the dynamic attributes of trajectories across various conditions. Additionally, we design a personalized pattern aggregation module to extract personalized driving behavior features. Extensive experimental on real-world datasets demonstrate the effectiveness and efficiency of ST-ECP.

We develop a Personal Knowledge Graph Question-Answering (PKGQA) assistant, seamlessly integrating information from multiple mobile applications into a unified and user-friendly query interface to offer users convenient information retrieval and personalized knowledge services. Based on a fine-grained schema customized for PKG, the PKGQA system in this paper comprises Symbolic Semantic Parsing, Frequently Asked Question (FAQ) Semantic Matching, and Neural Semantic Parsing modules, which are designed to take into account both accuracy and efficiency. The PKGQA system achieves high accuracy on the constructed dataset and demonstrates good performance in answering complex questions. Our system is implemented through an Android application, which is shown in https://youtu.be/p732U5KPEq4.

Existing knowledge graph query approaches, whether traditional textual query languages or visual query languages, have steep learning curves that are unfriendly for non-expert users. This demonstration presents a Visual Query approach based on Full-Text search for knowledge graphs, called VQFT, which simplifies the process of querying knowledge graphs for users. Inspired by full-text search techniques, VQFT aims to combine the user-friendliness of visual query with the intuitiveness of full-text search , enabling users to query knowledge graphs as straightforward as using a search engine. Faceted full-text indexes, visual query constructor , and an interactive user interface are designed to achieve this goal. User tests and surveys have demonstrated that VQFT is more user-friendly and easier to learn than existing methods, which simplifies the construction of knowledge graph queries for non-expert users.

Knowledge graphs (KGs) are commonly used as side information to enhance collaborative signals and improve recommendation quality. In the context of knowledge-aware recommendation (KGR), graph neural networks (GNNs) have emerged as promising solutions for modeling factual and semantic information in KGs. However, the long-tail distribution of entities leads to sparsity in supervision signals, which weakens the quality of item representation when utilizing KG enhancement. Additionally, the binary relation representation of KGs simplifies hyper-relational facts, making it challenging to model complex real-world information. Furthermore, the over-smoothing phenomenon results in indistinguishable representations and information loss.

Graph knowledge discovery from graph-structured data is a fascinating data mining topic in various domains, especially in the Internet of Things, where inferring the graph structure from such informative data can benefit many downstream tasks. Deep neural networks are typically used to perform such predictions, but they produce unreliable results without sufficient high-quality data. Therefore, researchers introduce lightweight statistical precision matrix learning to infer the graph structure in many IoT scenarios with limited communication and resolution of sensors. However, these methods still suffer from low-resolution data or the omission of hidden information in time-series data. To address the challenges, we propose a novel approach for Energy-efficient Dynamic Sparse Graph Structure Estimation with one-bit data, EDGE. Our method proposes a novel estimator to estimate the covariance matrix from one-bit data, and then utilize the covariance matrices to capture the dynamic structure. We theoretically demonstrate the effectiveness of the estimators by deriving two non-asymptotic estimation error bounds for the estimated covariance matrix and precision matrix, respectively. The theoretical results show that our method can achieve a consistent result of the precision matrix at the rate O(log p/n). On multiple synthetic and real-world datasets, the experimental results demonstrate that our proposed estimator is able to obtain a relatively high detection rate using one-bit data, which exceeds the baseline by 35%, and identify potentially perturbed nodes in real-time dynamic network inference.

Spiking Neural Networks (SNNs) are considered the next generation of deep neural networks for their computation efficiency and biological plausibility. Still, SNN models can be fooled with adversarial perturbations and noises. There is an urgent need for building a robust SNN model that can be deployed in safety-critical domains. Recent works successfully proposed some defense methods inspired by those designed for traditional deep neural network models. However, these methods neglect the inherent robustness of SNN models, which has been proven by previous studies. In this paper, we dedicate ourselves to improving the inherent robustness of SNN without additional training. To do that, we unveil that the success of most attacks relies on obfuscating the model activation. Inspired by this phenomenon, we propose a spiking neural network framework Channel-wise Activation Recalibration (CARE) to improve SNN inherent robustness, which is named CARENet. By analyzing the model activation pattern, we prove that the CARE module has a strong capability of activation preservation. We evaluate our method on three benchmarks. Under diverse attacks, including hybrid attacks using multiple attacks, our method shows significant accuracy gains compared to baselines. Furthermore, our framework achieves competitive performance on natural benchmarks.

Most methods for context-aware recommendation focus on improving the feature interaction layer, but overlook the embedding layer. However, an embedding layer with random initialization often suffers in practice from the sparsity of the contextual features, as well as the interactions between the users (or items) and context. In this paper, we propose a novel user-event graph embedding learning (UEG-EL) framework to address these two sparsity challenges. Specifically, our UEG-EL contains three modules: 1) a graph construction module is used to obtain a user-event graph containing nodes for users, intents and items, where the intent nodes are generated by applying intent node attention (INA) on nodes of the contextual features; 2) a user-event collaborative graph convolution module is designed to obtain the refined embeddings of all features by executing a new convolution strategy on the user-event graph, where each intent node acts as a hub to efficiently propagate the information among different features; 3) a recommendation module is equipped to integrate some existing context-aware recommendation model, where the feature embeddings are directly initialized with the obtained refined embeddings. Moreover, we identify a unique challenge of the basic framework, that is, the contextual features associated with too many instances may suffer from noise when aggregating the information. We thus further propose a simple but effective variant, i.e., UEG-EL-V, in order to prune the information propagation of the contextual features. Finally, we conduct extensive experiments on three public datasets to verify the effectiveness and compatibility of our UEG-EL and its variant.

Mobile internet users generate personal data on the devices all the time in this era. In this paper, we demonstrate a novel system for integrating the data of a user from different sources into a Personal Knowledge Graph, i.e., PKG. We show how a user's intention can be detected and how the personal data can be aligned and connected by the user behaviors. The constructed PKG allows the system makes reasonable and accurate recommendations for users by a "neural + symbolic'' approach across different services. Our system is shown in https://youtu.be/hWuo8KCDrto.

Link prediction, which centers on whether or not a pair of nodes is likely to be connected, is a fundamental problem in complex network analysis. Network-embedding-based link prediction has shown strong performance and robustness in previous studies on complex networks, recommendation systems, and knowledge graphs. This approach has certain drawbacks, however; namely, the hierarchical structure of a subgraph is ignored and the importance of different nodes is not distinguished. In this study, we established the Subgraph Hierarchy Feature Fusion (SHFF) model for link prediction. To probe the existence of links between node pairs, the SHFF first extracts a subgraph around the two nodes and learns a function to map the subgraph to a vector for subsequent classification. This reveals any link between the two target nodes. The SHFF learns a function to obtain a representation of the extracted subgraph by hierarchically aggregating the features of nodes in that subgraph, which is accomplished by grouping nodes with similar structures and assigning different importance to the nodes during the feature fusion process. We compared the proposed model against other state-of-the-art link-prediction methods on a wide range of data sets to find that it consistently outperforms them.

Knowledge graph (KG) embedding techniques represent entities and relations as low-dimensional, continuous vectors, and thus enables machine learning models to be easily adapted to KG completion and querying tasks. However, learned dense vectors are inefficient for large-scale similarity computations. Learning-to-hash is to learn compact binary codes from high-dimensional input data and provides a promising way to accelerate efficiency by measuring Hamming distance instead of Euclidean distance or dot-product. Unfortunately, most of learning-to-hash methods cannot be directly applied to KG structure encoding. In this paper, we introduce a novel framework for encoding incomplete KGs and graph queries in Hamming space. To preserve KG structure information from embeddings to hash codes and address the ill-posed gradient issue in optimization, we utilize a continuation method with convergence guarantees to jointly encode queries and KG entities with geometric operations. The hashed embedding of a query can be utilized to discover target answers from incomplete KGs whilst the efficiency has been greatly improved.We compared our model with state-of-the-art methods on real-world KGs. Experimental results show that our framework not only significantly speeds up the searching process, but also provides good results for unanswerable queries caused by incomplete information.

The rapidly increasing RDF data in the Linked Open Data (LOD) community project is a valuable resource for obtaining domain knowledge. However, RDF data of specific topics also shows a trend of being more decentralized and fragmented, which makes it difficult and inefficient for the users to get an overview of a specific topic and retrieve the desired information. In this paper, we demonstrate a novel system called KFM, which can aggregate the distributed RDF data of a topic according to the facets of this topic. KFM provides a new way for users to obtain and explore domain knowledge in the LOD cloud.