Graph Contrastive Learning (GCL) has emerged as a powerful paradigm for training Graph Neural Networks (GNNs) in the absence of task-specific labels. However, its scalability on large-scale graphs is hindered by the intensive message passing mechanism of GNN and the quadratic computational complexity of contrastive loss over positive and negative node pairs. To address these issues, we propose an efficient GCL framework that transforms the input graph into a compact network of interconnected node sets while preserving structural information across communities. We firstly introduce a kernelized graph community contrastive loss with linear complexity, enabling effective information transfer among node sets to capture hierarchical structural information of the graph. We then incorporate a knowledge distillation technique into the decoupled GNN architecture to accelerate inference while maintaining strong generalization performance. Extensive experiments on sixteen real-world datasets of varying scales demonstrate that our method outperforms state-of-the-art GCL baselines in both effectiveness and scalability.

Gang Hu, Yating Chen, Haiyan Ding, Wang Gao, Huang Jiajia, Min Peng, Qianqian Xie, Kun Yue. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood.By analyzing model-generated reasoning trajectories, we find that errors are not uniformly distributed but often originate from a small number of early transition points, after which reasoning remains locally coherent but globally incorrect.These transitions coincide with localized spikes in token-level entropy, and alternative continuations from the same intermediate state can still lead to correct solutions.Based on these observations, we introduce GUARD 1 , a targeted inference-time framework that probes and redirects critical transitions using uncertainty signals.Empirical evaluations across multiple benchmarks confirm that interventions guided by these failure dynamics lead to more reliable reasoning outcomes.Our findings highlight the importance of understanding when and how reasoning first deviates, complementing existing approaches that focus on scaling inference-time computation.

Situational visual impairments (SVIs) hinder mobile readability, causing discomfort and limiting information access. Building on prior work in adaptive typography and accessibility, this paper presents SituFont, a context-aware and human-in-the-loop adaptive typography adjustment approach that enhances smartphone mobile readability by dynamically adjusting font parameters based on real-time contextual changes. Using smartphone sensors and a human-in-the-loop approach, SituFont personalizes text presentation to accommodate personal factors (e.g., fatigue, distraction) and environmental conditions (e.g., lighting, motion, location). To inform its design, we conducted formative interviews (N=15) to identify key SVI factors and controlled experiments (N=18) to quantify their impact on optimal text parameters. A comparative user study (N=12) across eight simulated SVI scenarios demonstrated SituFont’s effectiveness in improving smartphone mobile readability in terms of improved efficiency and reduced workload compared with a non-trivial manual adjustment baseline.

The Mainstream 3D masked point modeling representation learning community typically employs predefined, fixed-ratio random or block masking strategies, aiming to obtain optimal representations and achieve high downstream performance. However, these empirical designs overlook the significant geometric information and structural importance differences that are inherent among different 3D points, leading to a suboptimal trade-off between the representation capture capabilities and reconstruction difficulty of such masking strategies. To address this issue, we are the first to present this decision-making problem to a reinforcement learning agent and propose a Reinforcement Masked Autoencoder for 3D representation learning, named Point-RMAE. Guided by geometric features as state factor, this method leverages the Masking Strategy Analyzer and the Dynamic Masking Generator to adaptively decide and apply the masking strategy during pretraining. The Masking Ratio Scheduling module dynamically adjusts the masking ratio based on the optimal strategy. Subsequently, the analyzer is updated by multiscale rewards derived from reconstruction quality level, distribution-aware feedback, and policy exploration. Notably, to enrich the Reward Function with distribution-aware signals and avoid decision collapse issue, we propose a Flow Matching Point Cloud Fast Generator that guides the selected masking decisions. Our method achieves outstanding performance across downstream tasks such as shape classification, medical diagnosis, object detection, action recognition, denoising and multiscale scene segmentation on ten popular 3D and 4D datasets. More importantly, Point-RMAE pioneers the application of reinforcement learning in 3D self-supervised representation learning.

Training-free conditional generation based on flow matching aims to leverage pre-trained unconditional flow matching models to perform conditional generation without retraining. Recently, a successful training-free conditional generation approach incorporates conditions via posterior sampling, which relies on the availability of a score function in the unconditional diffusion model. However, flow matching models lack an explicit score function, rendering this strategy inapplicable. Approximate posterior sampling for flow matching has been explored, but it is limited to linear inverse problems. In this paper, we propose Flow Matching-based Posterior Sampling (FMPS) to broaden its scope of application. We introduce a correction term by steering the velocity field. This correction term can be reformulated to incorporate a surrogate score function, thereby bridging the gap between flow matching models and score-based posterior sampling. Hence, FMPS enables posterior sampling to be adjusted within the flow-matching framework. Furthermore, we propose two practical implementations of the correction mechanism: one to improve generation quality and the other to enhance computational efficiency. Experimental results on diverse conditional generation tasks demonstrate that our method achieves superior generation quality compared to existing state-of-the-art approaches, validating the effectiveness and generality of FMPS.

Towards Knowledge Graph (KG) completion, probabilistic logic reasoning approaches enable effective rule mining but incur high computational cost, while embedding-based methods offer high efficiency but confront limited semantic understanding. Neuro-symbolic approaches combine both by employing embeddings to approximate probabilistic distributions, yet face challenges in weight optimization and hurdles in scaling up from large probability graphs. To address these issues, we propose DPLogic, a differentiable probabilistic logic reasoning framework for KG completion. Initially, we construct a Markov logic network by selecting crucial formulas and constraining groundings to relevant subgraphs, effectively boosting the scalability of the framework. Subsequently, we represent formula weights through relation-specific embeddings by introducing neural logical operators, creating a differentiable pathway for end-to-end optimization. Finally, we obtain the distribution of unobserved KG triplets by facilitating the joint optimization of embedding-based and probabilistic distributions through an EM algorithm. Empirical findings on standardized datasets illustrate that our proposed DPLogic consistently surpasses state-of-the-art methodologies in terms of both efficacy and efficiency.

Multivariate time series (MTS) forecasting is crucial for predicting the future states of complexly coupled variables based on historical observations. To effectively capture the intricate interdependencies within MTS, graph-based methods have emerged as powerful tools. However, existing graph construction methods often produce structures that fail to preserve key temporal and cross-variable dependencies, introducing redundant or irrelevant connections. To address these challenges, we propose a structural entropy-based approach for MTS forecasting. The approach optimizes graph structures by reducing structural redundancy, thereby improving forecasting accuracy. Initially, we represent the temporal dependences by constructing an encoding tree incrementally. Through hierarchical organization of time steps, the temporal evolution is adaptively captured. Subsequently, we give the community-aware representation by building an encoding tree over the variables in MTS, extracting homogeneous communities from the tree structure while integrating community influence to better capture inter-variable dependencies. Finally,we present a training algorithm designed to generate accurate predictions for MTS, accompanied by a unified loss function that integrates forecasting inaccuracies with variations in structural entropy. Empirical findings on real-world datasets substantiate that our approach outperforms state-of-the-art models in capturing dependencies and enhancing forecasting precision.

Bayesian Network (BN) has been widely employed for many applications like medical diagnosis due to its ability to deal with probabilistic inferences. Real-world inference tasks in BN cannot be robustly processed by classic search-based inference algorithms, since the conditional probabilities w.r.t. given arbitrary evidence values may be missing (i.e., not included) in the conditional probability tables (CPTs). Most of the existing methods, relying on imputation models, density estimation models or deep neural networks, cannot accurately learn these missing probabilities. To this end, we incorporate the idea of learning and search for robust probabilistic inferences in BN. Firstly, we decompose the probabilistic inference task into missing and existing probability factors, ensuring the consistency of their probability spaces. Secondly, we define the Wasserstein distance between missing and existing probability factors, and incorporate the idea of generative adversarial network to obtain missing probability factors with the minimal Wasserstein distance. Finally, we give the algorithm for robust probabilistic inferences with arbitrary evidence values, which could also be used to deal with the probabilistic inferences with arbitrary query values. Extensive experiments on synthetic and real-world datasets are conducted to demonstrate the superiority of our proposed method.

Bayesian network (BN) structure learning on the discrete observations is crucial for representing uncertainty in data. However, existing single-structure learning methods are commonly trapped in local optimum or yielding structures that may lead to poorly calibrated predictions. Although posterior approximation methods can quantify the epistemic uncertainty over the learned BN structures, they cannot reliably identify the optimal BN structures. To tackle these issues, we propose a GFlowNet with Gradient-based Optimization (GFlowOpt) for the BN structure learning method. Initially, we employ Bayesian Information Criterion (BIC) scores as the rewards of BN structures, and adopt a contrastive learning-based training technique on GFlowNet to efficiently generate much better DAG representations. Subsequently, we train a proxy model on the continuous DAG representations by adopting the gradient-ascent-based optimization method to search more high proxy-scoring discrete candidate DAGs. Finally, we adopt Hill Climbing (HC) on these candidate DAGs to search high-scoring DAGs as the ultimate BN structures. Extensive experiments conducted on benchmark datasets demonstrate that the superiority of our proposed method compared with other state-of-the-art methods.

As the critical task in query optimization, cardinality estimation is fulfilled by learning the joint probability distribution of table attributes in most of the existing data-driven methods. However, these methods still suffer the efficiency bottleneck, since the exponential combinations of table joins lead to massive probability inferences. To address this issue, we propose the Bayesian Probability Forest (BPF) framework to reduce the calculation of probability inferences. By integrating mutual information and query frequency, we first propose a novel metric to learn the graphical structure of BPF, ensuring that the distance between high-frequency attributes and root node could be minimized. Then, we propose an efficient method for cardinality estimation in BPF. Specifically, the decomposition of cardinality estimation task is proposed to reduce the number of probability inferences, and elimination strategies are given to avoid the redundant calculations w.r.t. low-frequency attributes. Empirical investigations on real-world datasets demonstrate the superiority of our method over other cutting-edge competitors. Our codes are publicly available at https://github.com/CardEstGroup/bpf-ce.git.

As a fundamental task in the graph machine learning paradigm, link prediction aims to predict missing links in a graph. Recently, Graph Neural Networks (GNNs) have demonstrated significant superiority in learning graph representations and become the mainstream solution for link prediction tasks. However, existing GNN-based methods may exhibit suboptimal performance due to their inability to effectively distinguish automorphic nodes with identical structures. To address this issue, we propose a hierarchical structure-enhanced graph representation framework for link prediction based on structural information theory. Specifically, we first design an efficient algorithm to construct an encoding tree from the input graph by minimizing its structural entropy. The encoding tree is a multi-level hierarchical abstraction of the graph, providing an effective way to organize both global (higher levels) and local (lower levels) structural information for each node. Then, we enhance node embeddings with the hierarchical structural encoding, capturing nuanced structural patterns for distinguishing automorphic nodes. Finally, we train GNN models at different levels of the encoding tree to generate powerful link representations for prediction. Extensive experiments on several real-world datasets demonstrate the effectiveness and scalability of our proposed method. Our code is available at https://github.com/Bayunmaoyu/HSELP.

Multivariate time series forecasting remains a critical yet challenging task across various real-world applications, due to the complex inter-series and intra-series dependencies. While time series decomposition has emerged as a powerful paradigm for capturing intricate temporal patterns, many existing methods fail to fully exploit the predictive potential of the trend component, often relying on fixed decomposition strategies that may retain unpredictable or noisy elements. To address these limitations, we propose a complexity-aware trend extraction method that adaptively controls the complexity of the extracted trend, yielding a more predictable and robust trend component, thereby significantly improving forecasting accuracy. To better model inter-series dependencies and reduce noise interference in variable interactions, we introduce an information-theoretic constraint by leveraging mutual information to regulate the flow of information across variables. Furthermore, our framework strategically incorporates future trend characteristics into the forecasting process through a cross-attention mechanism that queries informative historical patterns, enabling more accurate predictions. Extensive experiments conducted on several real-world datasets demonstrate the effectiveness and superiority of our proposed method compared with other state-of-the-art methods. Our code is available at https://github.com/unarytree/MTSF.

Multivariate time series (MTS) forecasting endeavors to anticipate the forthcoming sequence of interdependent variables through the utilization of past observations. The prevailing methodologies, relying on deep neural networks, Transformer, or information bottleneck frameworks, persist in confronting challenges such as overlooking or inadequately capturing the inter / intra-series correlations evident in practical MTS datasets. In response to these challenges, we introduce a conditional information bottleneck-based strategy for MTS forecasting, grounded in information theory. Initially, we establish a conditional information bottleneck principle to capture the inter-series correlations via conditioning on non-target variables. Subsequently, a conditional mutual information-based technique is introduced to extract intra-series correlations by conditioning historical data, ensuring temporal consistency within each variable. Lastly, we devise a unified optimization objective and propose a training algorithm to collectively capture inter / intra-series correlations. Empirical investigations on authentic datasets underscore the superiority of our proposed approach over other cutting-edge competitors. Our code is available at https: //github.com/Xinhui-Lee/CIB-MTSF.

Mining the associations of electricity-carbon emission influencing factors is the basis for accurate prediction of carbon emissions. Traditional methods adopt statistical analysis of historical data to quantify the associations between electricity-carbon emission and various influencing factors. However, these methods still face challenges such as low accuracy and the inability to systematically incorporate domain knowledge when applied to large-scale electricity-carbon data. In this paper, we propose a knowledge graph (KG) based method for mining electricity-carbon emission influencing factors, starting from the question text that expresses the task of factor mining. Specifically, we first obtain the surrounding entities and relations in the electricity-carbon KG w.r.t. the topical entity in the question text, such that associative relations can be obtained and referred to as contextual relations. By incorporating the graph attention network, we enhance the base candidate sequence by adding more important contextual relations. Next, we give the idea for matching the given question and candidate relations via feedforward neural network and long short-term memory network. Ultimately, we present the training algorithm by max-pooling for feature vectors that reflect the matching degree to obtain a matching score. Entities in the sequences with higher scores, representing the most relevant carbon emission influencing factor, constitute the answer set. Experimental results verify the effectiveness of our proposed method.

Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose $\textbf{SY}$nergistic $\textbf{M}$ulti-agent $\textbf{P}$lanning with $\textbf{H}$eter$\textbf{O}$geneous la$\textbf{N}$gauge model assembl$\textbf{Y}$ ($\textbf{SYMPHONY}$), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.

Graph contrastive learning (GCL) has demonstrated remarkable success in training graph neural networks (GNNs) by distinguishing positive and negative node pairs without human labeling. However, existing GCL methods often suffer from two limitations: the repetitive message-passing mechanism in GNNs and the quadratic computational complexity of exhaustive node pair sampling in loss function. To address these issues, we propose an efficient and effective GCL framework that leverages community structure rather than relying on the intricate node-to-node adjacency information. Inspired by the concept of sparse low-rank approximation of graph diffusion matrices, our model delivers node messages to the corresponding communities instead of individual neighbors. By exploiting community structures, our method significantly improves GCL efficiency by reducing the number of node pairs needed for contrastive loss calculation. Furthermore, we theoretically prove that our model effectively captures essential structure information for downstream tasks. Extensive experiments conducted on real-world datasets illustrate that our method not only achieves the state-of-the-art performance but also substantially reduces time and memory consumption compared with other GCL methods. Our code is available at [https://github.com/chenx-hi/IGCL-CS](https://github.com/chenx-hi/IGCL-CS).

As the general description of relationships between attributes, approximate functional dependencies (AFDs) almost hold for a given dataset with a few violations. Most of existing methods for AFD discover are insufficient to balance the efficiency and accuracy due to the massive search space and permission of violations. To address these issues, we propose an efficient method of probabilistic semantics guided discovery of AFDs based on Bayesian network (BN). Firstly, we learn a BN structure and conduct conditional independence tests on the learned structure rather than the entire search space, such that candidate AFDs could be obtained. Secondly, we fulfill search space reduction and structure pruning by making use of probabilistic semantics of graphical models in terms of BN. Consequently, we provide a branch-and-bound algorithm to discover the AFDs with the highest smoothed mutual information scores. Experimental results illustrate that our proposed method is more effective and efficient than the comparison methods. Our code is available at [https://github.com/DKE-Code/BNAFD](https://github.com/DKE-Code/BNAFD).

The task of finding associative entities in knowledge graph (KG) is to provide a ranking list of entities according to their association degrees. However, many entities are not only linked in KG but also associated in terms of user behaviors, which facilitates finding associative entities accurately. This manuscript incorporates KG with user-generated data to propose the Association Entity Graph Model (AEGM) to evaluate the association degrees. They first propose the joint weighting function to evaluate the entity associations and prove its submodularity theoretically as well as the greedy algorithm to select the candidates efficiently. They define the entity association information to score the entity association and give the hill climbing search based algorithm for AEGM construction. Following, they embed AEGM to calculate the association degrees and obtain the associative entities efficiently. Extensive experiments on three datasets show that the proposed method can achieve a better performance than some state-of-the-art competitors in accurately finding associative entities.

Driven by the complementarity and consistency inherent in multiview data, multiview clustering (MVC) has garnered widespread attention in various domains. Real-world data often encounters the issue of missing information, leading to a surge of interest in the domain of incomplete MVC (IMVC). Despite existing approaches having made significant progress in addressing IMVC, two significant challenges persist: 1) many alignment-based methodologies tend to overlook the topological relationships among instances and 2) the view representations based on completion lack reconstructive properties, casting doubt on their alignment with the actual view representations. In response, we present a novel approach termed neighbor-based completion for addressing IMVC (NBIMVC), which capitalizes on the topological information among instances and the consistent information across views. Specifically, our method uses autoencoders to learn feature representations for each view and leverages nearest-neighbor relationships between unique and complete instances to complete missing features in missing views. Subsequently, we enforce hard negative alignment constraints on complete paired instances in the feature space. Finally, we ensure the consistency of views in the semantic space by employing cluster information and a shared clustering network, which facilitates the final multiview categories output and effectively resolves the IMVC problem. Extensive experimental evaluations validate the efficacy of our proposed method, showcasing comparable or superior performance to existing approaches.

As one of the most common tasks in graph data analysis, node classification is frequently solved by using graph structure learning (GSL) techniques to optimize graph structures and learn suitable graph neural networks. Most of the existing GSL methods focus on fusing different structural features (basic views) extracted from the graph, but very little graph semantics, like hierarchical communities, has been incorporated. Thus, they might be insufficient when dealing with the graphs containing noises from real-world complex systems. To address this issue, we propose a novel and effective GSL framework for node classification based on the structural information theory. Specifically, we first prove that an encoding tree with the minimal structural entropy could contain sufficient information for node classification and eliminate redundant noise via the graph's hierarchical abstraction. Then, we provide an efficient algorithm for constructing the encoding tree to enhance the basic views. Combining the community influence deduced from the encoding tree and the prediction confidence of each view, we further fuse the enhanced views to generate the optimal structure. Finally, we conduct extensive experiments on a variety of datasets. The results demonstrate that our method outperforms the state-of-the-art competitors on effectiveness and robustness.

Bayesian network (BN) is a directed acyclic graph (DAG) representing the dependence relations among random variables with conditional probability tables (CPTs). The efficiency and accuracy of multiple probabilistic inferences in BN could not be guaranteed by most of the existing approximate inference methods. To address this issue, we propose the methods of Transformer based BN embedding (TBNE) and TBNE based probabilistic inferences. Specifically, we first adopt mutual information to measure the weight of parent-child node pairs and transform BN into multiple bidirectional weighted graphs (BWGs), while preserving the DAG and CPTs. Then, we redesign the Transformer model by incorporating the node importance and shortest path encodings, and extend the self-attention module of Transformer to generate node embeddings of BWGs. Following, we cast the probabilistic inference as the decoding information maximization of the path in BN from the perspective of information theory. Finally, we give an efficient algorithm for multiple probabilistic inferences by calculating embedding similarities between evidence and query nodes in BN. Experimental results show that our inference method is more efficient than the state-of-the-art competitors by several orders of magnitude while maintaining almost the same results.

Abstract When detecting the objects in videos, motion always leads to object deterioration, like blurring and occlusion, as well as the strange state of the object's shape and posture. Consequently, the detection of video frames will lead to a decline in accuracy by using the image object detection model. This paper proposes an online video object detection method based on the one‐stage detector YOLOx. First, the module for space–time feature aggregation is given, which uses the space–time information of past frames to enhance the feature quality of the current frame. Then, the module for result reuse is given, which incorporates the detection results of past frames to improve the detection stability of the current frame. By these two modules, the trade‐off between accuracy and speed of video object detection could be achieved. Experimental results on the ImageNet VID show the improvement of speed and accuracy of the proposed method.

Abstract Knowledge graph (KG) has become the vital resource for various applications like question answering and recommendation system. However, several relations in KG only have few observed triples, which makes it necessary to develop the method for few-shot relation prediction. In this paper, we propose the Convolutional Neural Network with Self-Attention Relation Prediction (CARP) model to predict new facts with few observed triples. First, to learn the relation property features, we build a feature encoder by using the convolutional neural network with self-attention from the few observed triples rather than background knowledge. Then, by incorporating the learned features, we give an embedding network to learn the representation of incomplete triples. Finally, we give the loss function and training algorithm of our CARP model. Experimental results on three real-world datasets show that our proposed method improves Hits@10 by 48% on average over the state-of-the-art competitors.

In the deep neural network based few-shot learning, the limited training data may make the neural network extract ineffective features, which leads to inaccurate results. By Bayesian graph neural network (BGNN), the probability distributions on hidden layers imply useful features, and the few-shot learning could improved by establishing the correlation among features. Thus, in this paper, we incorporate mutual information (MI) into BGNN to describe the correlation, and propose an innovative framework by adopting the Bayesian network with continuous variables (BNCV) for effective calculation of MI. First, we build the BNCV simultaneously when calculating the probability distributions of features from the Dropout in hidden layers of BGNN. Then, we approximate the MI values efficiently by probabilistic inferences over BNCV. Finally, we give the correlation based loss function and training algorithm of our BGNN model. Experimental results show that our MI based BGNN framework is effective for few-shot learning and outperforms some state-of-the-art competitors by large margins on accuracy.

By analyzing users’ behavior data for personalized services, most state-of-the-art methods for user preference modeling are often based on batch-mode machine learning algorithms, where all rating data are assumed to be available throughout the training process. However, data in the real world often arrives sequentially and user preference may change dynamically. The real-time characteristics of rating data make the algorithms for preference modeling challenging to suit real-world online applications. By the user preference model (UPM) based on Bayesian network with a latent variable (BNLV), uncertain relationships among relevant attributes of users, objects and ratings could be represented, in which user preference is represented by the latent variable. In this paper, we propose an online approach for parameter learning of UPM. Specifically, we first extend the classic Voting EM algorithm by using Bayesian estimation in terms of the situation with latent variables. Consequently, we propose the algorithm for learning parameters of UPM from few and sequentially-changing rating data to reflect the gradually changing preferences. Finally, we test the effectiveness of our proposed algorithm by conducting experiments on various datasets. Experimental results demonstrate the superiority of our method in various measurements.

Recent advances in localization techniques have fundamentally enhanced social networking services, allowing users to share their locations and location-related contents. This has further increased the popularity of location-based social networks (LBSNs) and produces a huge amount of trajectories composed of continuous and complex spatio-temporal points from people’s daily lives. How to accurately aggregate large-scale trajectories is an important and challenging task. Conventional clustering algorithms (e.g., k -means or k -mediods) cannot be directly employed to process trajectory data due to their serialization, triviality and redundancy. Aiming to overcome the drawbacks of traditional k -means algorithm and k -mediods, including their sensitivity to the selection of the initial k value, the cluster centers and easy convergence to a locally optimal solution, we first propose an optimized k -means algorithm (namely OKM ) to obtain k optimal initial clustering centers based on the density of trajectory points. Second, because k -means is sensitive to noisy points, we propose an improved k -mediods algorithm called IKMD based on an acceptable radius r by considering users’ geographic location in LBSNs. The value of k can be calculated based on r , and the optimal k points are selected as the initial clustering centers with high densities to reduce the cost of distance calculation. Thirdly, we thoroughly analyze the advantages of IKMD by comparing it with the commonly used clustering approaches through illustrative examples. Last, we conduct extensive experiments to evaluate the performance of IKMD against seven clustering approaches including the proposed optimized k -means algorithm, k -mediods algorithm, traditional density-based k -mediods algorithm and the state-of-the-arts trajectory clustering methods. The results demonstrate that IKMD significantly outperforms existing algorithms in the cost of distance calculation and the convergence speed. The methods proposed is proved to contribute to a larger effort targeted at advancing the study of intelligent trajectory data analytics.

As the number of Web APIs ever increases, choosing the appropriate APIs for mashup creations becomes more difficult. To tackle this problem, various methods have been proposed to recommend APIs to match requirements of mashups and achieved much success. However, there existed some challenges with feature fusion and utilization, textual requirement understanding, utilization of Mashup categories and compatibility evaluation. Therefore, we propose a neural framework (MTFM) based on multi-model fusion and multi-task learning for Mashup-oriented Web API recommendation. MTFM exploits a semantic component to generate representations of requirements and introduces a feature interaction component to model the feature interaction between mashups and Web APIs. Output features of both components are further fused to predict the candidate APIs, and this enables us to have both the advantages of content-based and collaborative filtering methods. We further introduce mashup category judgment as an auxiliary task, where both tasks are viewed as a multi-label learning problem and jointly optimized with multi-task learning. Also, we have extended MTFM to MTFM++ to take advantage of the metadata and quality features of APIs, and proposed a metric for compatibility evaluation. Experimental results on the ProgrammableWeb dataset show that our methods outperform most popular state-of-the-art methods.

MOTIVATION: There is growing evidence showing that the dysregulations of miRNAs cause diseases through various kinds of the underlying mechanism. Thus, predicting the multiple-category associations between microRNAs (miRNAs) and diseases plays an important role in investigating the roles of miRNAs in diseases. Moreover, in contrast with traditional biological experiments which are time-consuming and expensive, computational approaches for the prediction of multicategory miRNA-disease associations are time-saving and cost-effective that are highly desired for us. RESULTS: We present a novel data-driven end-to-end learning-based method of neural multiple-category miRNA-disease association prediction (NMCMDA) for predicting multiple-category miRNA-disease associations. The NMCMDA has two main components: (i) encoder operates directly on the miRNA-disease heterogeneous network and leverages Graph Neural Network to learn miRNA and disease latent representations, respectively. (ii) Decoder yields miRNA-disease association scores with the learned latent representations as input. Various kinds of encoders and decoders are proposed for NMCMDA. Finally, the NMCMDA with the encoder of Relational Graph Convolutional Network and the neural multirelational decoder (NMR-RGCN) achieves the best prediction performance. We compared the NMCMDA with other baselines on three experimental datasets. The experimental results show that the NMR-RGCN is significantly superior to the state-of-the-art method TDRC in terms of Top-1 precision, Top-1 Recall, and Top-1 F1. Additionally, case studies are provided for two high-risk human diseases (namely, breast cancer and lung cancer) and we also provide the prediction and validation of top-10 miRNA-disease-category associations based on all known data of HMDD v3.2, which further validate the effectiveness and feasibility of the proposed method.

Existing software tools for topology-based pathway enrichment analysis are either computationally inefficient, have undesirable statistical power, or require expert knowledge to leverage the methods' capabilities. To address these limitations, we have overhauled NetGSA, an existing topology-based method, to provide a computationally-efficient user-friendly tool that offers interactive visualization. Pathway enrichment analysis for thousands of genes can be performed in minutes on a personal computer without sacrificing statistical power. The new software also removes the need for expert knowledge by directly curating gene-gene interaction information from multiple external databases. Lastly, by utilizing the capabilities of Cytoscape, the new software also offers interactive and intuitive network visualization.

Bike-sharing systems are becoming popular and generate a large volume of trajectory data. In a bike-sharing system, users can borrow and return bikes at different stations. In particular, a bike-sharing system will be affected by weather, the time period, and other dynamic factors, which challenges the scheduling of shared bikes. In this article, a new shared-bike demand forecasting model based on dynamic convolutional neural networks, called SDF , is proposed to predict the demand of shared bikes. SDF chooses the most relevant weather features from real weather data by using the Pearson correlation coefficient and transforms them into a two-dimensional dynamic feature matrix, taking into account the states of stations from historical data. The feature information in the matrix is extracted, learned, and trained with a newly proposed dynamic convolutional neural network to predict the demand of shared bikes in a dynamical and intelligent fashion. The phase of parameter update is optimized from three aspects: the loss function, optimization algorithm, and learning rate. Then, an accurate shared-bike demand forecasting model is designed based on the basic idea of minimizing the loss value. By comparing with classical machine learning models, the weight sharing strategy employed by SDF reduces the complexity of the network. It allows a high prediction accuracy to be achieved within a relatively short period of time. Extensive experiments are conducted on real-world bike-sharing datasets to evaluate SDF. The results show that SDF significantly outperforms classical machine learning models in prediction accuracy and efficiency.

Reputation system is an important means to build trust, aid decision making of users, and sustain user loyalty in the context of online services. However, different users inherently have different preferences, and so it is impossible that all users rate services with the same criteria. Thus, aggregating cardinal ratings into reputation will potentially lead to unreliable and misleading result, which makes the impossibility of interpersonal utility comparisons should be considered in reputation systems. In this paper, we propose a novel reputation measurement mechanism that aggregates ordinal user preferences rather than cardinal ratings into reputation. By extending the majority rule naturally, dominance relationship between services is defined based on ordinal preferences. Then, reputation measurement is modelled as a problem to find a ranking that indicates the dominance relationships among services. A directed acyclic graph is constructed based on the dominance relationships of services pairs and then the ranking of services is found from the graph. We prove our method satisfies some basic criteria that a reasonable reputation measurement method should satisfy in the context of the impossibility of interpersonal utility comparisons. We also conduct a comprehensive experimental study and performance analysis to evaluate the effectiveness and efficiency of the proposed method.

In recent years, various collaborative QoS prediction methods have been put forward to coping with the demand for efficient quality-of-service (QoS) evaluation, by drawing lessons from the recommender systems. However, there still remain some challenging issues on this direction, as how to effectively exploit complex contexts to improve prediction accuracy, and how to realize collaborative QoS prediction of multiple attributes. Inspired by the principles of deep learning, we have proposed a universal deep neural model (DNM) for making multiple attributes QoS prediction with contexts. In this model, contextual features are mapped into a shared latent space to semantically characterize them in the embedding layer. The contextual features with their higher-order interactions are captured through the interaction layer and the perception layers. Multi-tasks prediction is realized by stacking task-specific perception layers on the shared neural layers. Armed with these, DNM provides a powerful framework to integrate with various contextual features to realize multi-attributes QoS prediction. Experimental results from a large-scale QoS-specific dataset demonstrate that DNM achieves superior prediction accuracy in term of mean absolute error (MAE) compared with the state-of-the-art collaborative QoS prediction techniques. Additionally, the DNM model has a good robustness and extensibility on exploiting heterogeneous contextual features.

A core source of raw information used as inputs to the reputation systems of online services is the feedback ratings provided by users. However, it is impossible that all users rate services with the same criteria and so ratings of different users are incommensurable. Meanwhile, users are not necessarily willing to provide honest feedbacks. Thus, aggregating dishonest cardinal ratings into reputation will potentially lead to unreliable and misleading reputation. In this paper, we propose a reputation model that aggregates ordinal user preferences rather than cardinal ratings for online services with user incentive. A distance metric is defined to measure the discrepancy between ordinal preferences. Then an optimal reputation model with the attributes of incentive compatible and individually rational is proposed. We design a B&B algorithm to solve the optimization problem so that a reputation vector that maximizes the total value of all users can be found efficiently. A comprehensive experimental study and performance analysis are conducted to evaluate the effectiveness and efficiency of the proposed method.

Crowdsourcing labeling systems provide an efficient way to generate multiple inaccurate labels for given observations. If the competence level or the "reputation," which can be explained as the probabilities of annotating the right label, for each crowdsourcing annotators is equal and biased to annotate the right label, majority voting (MV) is the optimal decision rule for merging the multiple labels into a single reliable one. However, in practice, the competence levels of annotators employed by the crowdsourcing labeling systems are often diverse very much. In these cases, weighted MV is more preferred. The weights should be determined by the competence levels. However, since the annotators are anonymous and the ground-truth labels are usually unknown, it is hard to compute the competence levels of the annotators directly. In this paper, we propose to learn the weights for weighted MV by exploiting the expertise of annotators. Specifically, we model the domain knowledge of different annotators with different distributions and treat the crowdsourcing problem as a domain adaptation problem. The annotators provide labels to the source domains and the target domain is assumed to be associated with the ground-truth labels. The weights are obtained by matching the source domains with the target domain. Although the target-domain labels are unknown, we prove that they could be estimated under mild conditions. Both theoretical and empirical analyses verify the effectiveness of the proposed method. Large performance gains are shown for specific data sets.

Bayesian network (BN) is the well-accepted framework for representing and inferring uncertain knowledge. To learn the BN-based uncertain knowledge incrementally in response to the new data is useful for analysis, prediction, decision making, etc. In this paper, we propose an approach for incremental learning of BNs by focusing on the incremental revision of BN’s graphical structures. First, we give the concept of influence degree to describe the influence of new data on the existing BN by measuring the variation of BN’s probability parameters w.r.t. the likelihood of the new data. Then, for the nodes ordered decreasingly by their influence degrees, we give the scoring-based algorithm for revising BN’s subgraphs iteratively by hill-climbing search for reversing, adding or deleting edges. In the incremental revision, we emphasize the preservation of probabilistic conditional independencies implied in the BN based on the concept and properties of Markov equivalence. Experimental results show the correctness, precision and efficiency of our approach.

Noise can play beneficial roles in neural network systems from biology to neuromorphic computing through stochastic resonance, averaging signals, and other mechanisms. To achieve the benefits of noise in neuromorphic circuits, we propose a random pulse generator(RPG) as a source of noise and describe its implementation in neuromorphic circuits. The RPG includes three components: an LED, a wave guide, and a single-photon avalanche diode(SPAD). The LED will generate photons in Poisson-distributed time intervals with Gaussian-distributed amplitude. Through a wave guide, the SPAD senses the photons and generate uV wavelength random pulses. The noise can be implemented in a discrete manner by connecting to an amplifier and in a continuous manner by connecting to a current mirror. The design was simulated using CMOS 180nm SPICE models. The generated variable signals are used in different parts of a BioRC neuromorphic neuron to implement a noisy neuron following different neurological findings. The noisy neuron's random postsynaptic potential(PSP), along with mechanisms to support stochastic resonance, noise inhibition and noise-forced spiking were demonstrated.

Different kinds of illustrations and artistic imagery can be generated or simulated through the nonphotorealistic rendering (NPR) technique. However, designing and simulating new NPR artistic styles remains extremely challenging. Chalk art style is a very famous artistic work all over the world, and few algorithms have been put forward to illustrate this style. This paper presents a novel NPR technique which generates a chalk art drawing from a 2D photograph automatically. We aim at obtaining a set of lines surface with coarse appearance and generating stroke textures of the real chalk painting. Firstly, the edge of the source image is extracted by difference-of-Gaussian filter method. To simulate chalk painting’s lines, image diffusion and enhancement techniques are proposed to produce coarse and rough lines. Secondly, we developed an improved line integral convolution and dilation operation methods to produce the chalk stroke texture. Finally, the edge image, stroke texture image and color image will be mapped to another background image to generate the chalk art drawing. Experimental results are presented to show the effectiveness of our method in producing the color chalk stylistic illustrations, and the methods can simulate the characters of the real chalk art painting. The proposed method of this paper will enlarge the research and application fields of NPR. Meanwhile, it provides a tool for the user to create chalk art paintings via computers even without painting skill.

Reputation systems have become an important means to help users build trust, reduce information asymmetry and filter information in the context of online services provision. Different users cannot rate services under the same criteria due to the scale and dynamism of these systems. Thus, aggregating cardinal ratings into reputation will potentially lead to unreliable and misleading result, which makes reputation systems necessarily consider the impossibility of interpersonal utility comparisons. In this paper, we exploit the ordinal user preferences between services to compute reputation of services. A distance metric is defined to measure the discrepancy between two rating vectors and the reputation computation problem was formalized as an optimization problem. Then, genetic algorithm is used to solve the optimization problem to find a reputation vector that minimizes the total number of disagreements with the rating matrix. We conduct a comprehensive experimental study and performance analysis to evaluate the effectiveness and efficiency of the proposed method.

With the rapid development of wearable sensors and pervasive computing technologies including smartphones, acceleration-based human activity recognition is receiving increased attention for medical research applications. Motivated by the “weightlessness” feature, here we apply a bidirectional feature during the feature extraction phase of activity recognition; however, since the bidirectional feature has two components, they cannot simply be concatenated into a long vector, but can be naturally treated as a second-order tensor. Therefore, we propose a new tensor-based feature selection method termed tensor manifold discriminant projections (TMDP). TMDP simultaneously considers: 1) applying an optimization criterion that can directly process the tensor spectral analysis problem, thereby decreasing the computational cost compared to traditional tensor-based feature selection methods; 2) extracting local rank information by finding a tensor subspace that preserves the rank order information of the within-class input samples; and 3) extracting discriminant information by maximizing the sum of distances between every sample and their interclass sample mean. Experiments on the naturalistic mobile devices-based human activity 2.0 dataset are performed to demonstrate the effectiveness and robustness of TMDP.

Recently, there has been much more attention focusing on the evolving networks, whose application domains include Web networks, social networks, communication networks and etc. In this paper, we focus on a financial network, where nodes represent participants of a financial market. Due to lending activities, funds are transferred from one participant to another, and credit-debt relationships between them are formed. With repeated activities, flows of funds are shown in a financial network. We analyze the evolution of funds flows based on evolutionary game theory. Using Lyapunov stability method, we prove that funds flows converge to a relatively stable state, and prove a bound on the convergence time. Finally, we design an ant colony optimization algorithm for a financial network, and use experiments to simulate the evolving process of funds flows.

The performance of vector graphics render has always been one of the key elements in mobile devices and the most important step to improve the performance is to enhance the efficiency of polygon fill algorithms. In this paper, we proposed a new and more efficient polygon fill algorithm based on the scan line algorithm and Grid Fill Algorithm (GFA). First, we elaborated the GFA through solid fill. Second, we described the techniques for implementing antialiasing and self-intersection polygon fill with GFA. Then, we discussed the implementation of GFA based on the gradient fill. Generally, compared to other fill algorithms, GFA has better performance and achieves faster fill speed, which is specifically consistent with the inherent characteristics of mobile devices. Experimental results show that better fill effects can be achieved by using GFA.

Reviews are contents written by users to express opinions on products or services. However, the number of reviews is always large and the quality of reviews is various. In order to assess the quality of reviews, we ought to know the factors that have influence on or are related to the quality of reviews. In this paper, we present an in-depth study of reviews on JD.com, one of the famous E-commerce sites in China. We observed the times when users buy goods are highly related to the time when they post reviews. Meanwhile, the level of users is an important factor affects the quality of reviews. On the other hand, users prefer to post short reviews containing the description of the quality and price of the product. Based on a lexical resource containing sentiment annotations, we found sentimental words expressing users' feelings and opinions is one of the key factors that can influence the quality of reviews. Finally, we evaluated the importance of more than 18 factors influencing the quality of reviews, and found these factors can be compressed into 5 principal factors.

Bayesian network (BN) has been adopted as the underlying model for representing and inferring uncertain knowledge. As the basis of realistic applications centered on probabilistic inferences, learning a BN from data is a critical subject of machine learning, artificial intelligence, and big data paradigms. Currently, it is necessary to extend the classical methods for learning BNs with respect to data-intensive computing or in cloud environments. In this paper, we propose a parallel and incremental approach for data-intensive learning of BNs from massive, distributed, and dynamically changing data by extending the classical scoring and search algorithm and using MapReduce. First, we adopt the minimum description length as the scoring metric and give the two-pass MapReduce-based algorithms for computing the required marginal probabilities and scoring the candidate graphical model from sample data. Then, we give the corresponding strategy for extending the classical hill-climbing algorithm to obtain the optimal structure, as well as that for storing a BN by pairs. Further, in view of the dynamic characteristics of the changing data, we give the concept of influence degree to measure the coincidence of the current BN with new data, and then propose the corresponding two-pass MapReduce-based algorithms for BNs incremental learning. Experimental results show the efficiency, scalability, and effectiveness of our methods.

The complexity of Web services composition process is intuitively relevant to the effects such as readability, testability, reliability, and maintainability. Analyzing the complexity at all stages of process design and development helps avoid the drawbacks associated with high-complexity processes. In this paper, we present a control-flow complexity measure of the structured process of Web service composition. The measure is defined based on a data structure named Structure Tree. By the complexity computing algorithm based on Structure Tree, we can get complexity of a process and its substructures simultaneously. The characteristics of different structure types and the nesting level are taken into consideration in the complexity measure. Since Weyuker's properties are a widely known formal analytical approach of complexity metric, we evaluate our measure in terms of these properties in order to guarantee its effectiveness.

This paper is to compute a Nash equilibrium in a fuzzy environment, which is represented by a fuzzy approximate Nash equilibrium in a space of discrete mixed strategies. For discrete mixed strategies, the relationship between the discrete degree and the approximate degree is discussed. Based on the fuzzy regret degree, a genetic algorithm for computing a fuzzy Nash equilibrium is given.

Recently, Web services have become a new technology trend for Enterprise Application Integration (EAI) and more and more applications based on Web services are emerging. One of the problems in using Web services in business applications such as logistics is services composition automatically and efficiently. In this paper, we present a Dynamic, Demand-Driven Web services Engine called D3D-Serv to implement composite service functionality that is used to dynamically build composite services from existing services according to different business logics and requirements. In this D3D-Serv framework, the most challenging function to implement is dynamic selection of service providers at run time. The highly dynamic and distributed nature of Web services often makes some service providers overloaded at certain times while others idle. To solve this problem, we propose an efficient services selection and execution strategy that is based on the queuing theory and can provide guarantees for the QOS (Quality of Service) under provider's limited resources. Preliminary experimental results have shown that this algorithm is effective.