Deep multi-modal clustering fully learns semantically consistent and discriminative cluster representations between multiple modalities in an unlabeled manner. However, existing methods treat all samples equally, ignoring varying sample quality, which limits clustering performance. Inspired by the concept of interest in the recommendation system, we propose a novel interest-driven deep multi-modal clustering (IDMC) framework. It designs a new paradigm to quantify the importance of each sample base on the attention it receives from other samples, which called interest value. This value jointly captures the local geometric structure through the Euclidean distance in feature space and the consistency of pseudo-labels. Then, we design a novel adaptive Bayesian fusion mechanism to dynamically balance the prior features and self-supervisory signals to ensure confidence-based sample importance estimation. Furthermore, we introduce a median normalization constraint and a label consistency constraint to further refine the construction of the interest value. By embedding this interest-guided value into representation learning and cluster optimization, IDMC focuses on the samples with the most information and the most stable semantics, thereby enhancing the performance of multi-modal representation learning. Extensive experiments verify that IDMC is superior to existing state-of-the-art methods in multiple evaluation metrics.

Recently, graph contrastive learning (GCL) has attracted considerable attention in social recommendation, owing to its ability to enhance the robustness of node embedding learning against noise and data sparsity. Despite their effectiveness, we argue that existing GCL-based methods remain limited by three key issues: (1) during graph propagation, they rely on uniform neighbor aggregation and non-adaptive embedding readout, leading to suboptimal node representations; (2) when constructing contrastive views, they typically adopt graph augmentations based on stochastic perturbations of graph-structured data, which may undermine model fidelity; (3) during model optimization, they treat all observed instances equally, forgoing the subtle difference of each positive sample at different training periods. To address these limitations, we propose an effective and efficient GCL framework (EGCL) for social recommendation. Specifically, we devise a graph adaptive propagation module to learn informative embeddings of all items and users. Furthermore, we devise an augmentation-free dual CL paradigm, which consists of intra-CL within a single domain and inter-CL between two separate domains. In addition, we develop a self-adaptive weighted supervised learning paradigm and formulate the whole training procedure as a bi-level optimization problem. Extensive experiments are performed on four benchmarks, demonstrating the effectiveness and efficiency of EGCL over recent state-of-the-art recommenders. Our implementation and datasets are available at https://github.com/wubinzzu/EGCL .

Temporal knowledge graph (TKG) reasoning is potent for discovering plausible facts with observable knowledge. However, evolving TKGs often bring newly unseen entities, relations, and timestamps, which pose significant challenges for current TKG reasoning methods as they struggle to extrapolate facts involving unseen components. We term this realistic yet under-investigated problem as full extrapolation over TKGs, aiming to model all unseen components for reasoning within evolving TKGs. To tackle this, we propose a novel contrastive variational graph symmetric autoencoder (CVGSAE) framework under the meta-learning setting. Initially, we first extract the spatiotemporal connections between relations and integrate a functional time encoding strategy to simultaneously initialize unseen entities, relations, and timestamps. Subsequently, we design an interactive variational graph symmetric autoencoder to encode and then reconstruct entity and relation representations by capturing their interactions to generate contrastive views. Finally, a dual-contrastive learning scheme is imposed on the encoded and reconstructed representations of both entities and relations to enhance their discriminability and task relevance. Extensive experiments on two benchmark datasets demonstrate that CVGSAE yields significant advancements beyond state-of-the-art baselines across all evaluation metrics. The source code is available at:https://github.com/hcfun/CVGSAE

Deep multi-modal clustering can extract useful information among modals, thus benefiting the final clustering and many related fields. However, existing multi-modal clustering methods have two major limitations. First, they often ignore different levels of guiding information from both the feature representations and cluster assignments, which thus are difficult in learning discriminative representations. Second, most methods fail to effectively eliminate redundant information between multi-modal data, negatively affecting clustering results. In this paper, we propose a novel multi-aspect self-guided deep information bottleneck (MSDIB) method for multi-modal clustering, which can effectively employ different aspects of guiding information for learning cluster-friendly information among modals. MSDIB mainly contains two parts: information compression and information preservation. In information compression, we extract from the private information of each modality to obtain the compact representation and meanwhile conduct mutual compression between them. In information preservation, the aim is to preserve the shared information among modals and the self-supervised information from the clustering results in each iteration. In the above process, there are mainly three aspects of self-guiding information, the modality-private information, the modality-shared information and the self-supervised pseudo label information. By minimizing the mutual information based objective function with a variational optimization method, we can fully extract useful discriminative information while eliminating the irrelevant parts. Extensive experimental results demonstrate that our method outperforms state-of-the-art multi-modal clustering methods, showcasing its superior performance and broad application prospects.

Multi-view clustering (MVC), especially contrastive MVC, has demonstrated promising potential in many fields and practical scenarios. However, existing contrastive MVC methods still ignore the reliability of clustering results and the impact of false negative pairs, which limits the application of methods in critical security areas. To solve the above challenges, we propose a Self-supervised Trusted Contrastive Multi-view Clustering with Uncertainty Refined (STCMC-UR) method, which integrates clustering results and uncertainty learning to guide the self-supervised contrastive learning (CL). First, the belief of a specific view is generated in the evidence generation module. Afterwards, the belief mass and uncertainty of each view are learned using the Dirichlet distribution and we fuse multiple views with the Dempster-Shafer theory to generate the final clustering result and the uncertainty of the view. Then, the view weight is further quantified to adjust the belief of each view. Different from existing methods, with the clustering result and uncertainty generated by the fusion, we design a feature-level uncertainty-refined self-supervised CL module, where the pseudo-label is selectively employed in each iteration to conduct more accurate CL. As a result, the modules are mutually beneficial, which is conducive to more effective feature learning and clustering structure discovery, and more accurate learning results are obtained. Extensive experiments on five datasets show that the proposed method has significant improvements in effectiveness compared with the latest methods.

Multi-modal knowledge graph reasoning (MKGR) seeks to conjecture plausible facts in MKGs by learning effective representations from various modalities (e.g., structure, text, and image). However, due to holistic redundancy (i.e., each modality carries task-irrelevant redundancy) and modality conflict (i.e., different modalities contain contradictory information), the reasoning performance of current methods is substantially impaired. In this paper, we propose a novel Consistency Discovery-guided Information Bottleneck (CDIB) framework to address the aforementioned challenges. Specifically, a modality compression module is first designed to learn modality-private entity representations of alleviating redundant information. Then, a consistency discovery module is developed to discover cross-modal consistency during multi-modal fusion to learn the comprehensive entity representations. To retain task-relevant information, an information preservation module is devised to further enrich the comprehensive entity representations to be predictive for MKGR. Extensive experiments indicate that CDIB achieves state-of-the-art reasoning ability on two benchmark datasets over current MKGR baselines, and also exhibits promising robustness against noise.

Next-item recommendation has received considerable attention in academia and industry, which aims to predict the next desired item for each user based on his historical behaviors. It has been validated that user behaviors are driven by two key factors:social influence, which leverages social relationships to better infer user preference, andsequential influence, which captures item transition patterns to model the dynamic evolution of user interest. While previous next-item recommenders have made great progress, we argue that there still exist three critical limitations: (1) they always follow the paradigm of entangling social and sequential influences, resulting in poor interpretability; (2) they fail to explicitly capture high-order influences at social-level and sequential-level, resulting in the suboptimal performance; (3) they fail to dynamically distinguish the importance of each influence factor when predicting user preference. To settle these three defects, we contribute a novel solution for socially-aware next-item recommendation, namely Disentangled Graph Contrastive Learning (DGCL) method, which explicitly disentangles social and sequential influences on user behavior data. Specifically, we first reorganize social relationships and all users' behavior sequences as two separate graphs. Then, a disentangled graph propagation module is developed on these two graphs to independently capture high-order influences at social-level and sequential-level. Furthermore, we formalize a dual contrastive learning paradigm as an auxiliary task to supervise the thorough disentanglement. Finally, we devise a user-specific attention mechanism to adaptively differentiate the importance of each influence factor for model prediction. Empirical results on four benchmark datasets demonstrate the superiority of DGCL over recent state-of-the-art recommenders. Further analysis verifies the rationality and necessity of each part in our solution. Our implemented codes and used datasets are available athttps://github.com/wubinzzu/DGCL.

The development of industrial Internet of Things (IoT) generates massive unlabeled multimodal data. multimodal clustering (MMC) methods can unsupervisedly learn reasonable clustering structures by mining the complementary information in each modality, which has become one of the essential critical technologies in industrial IoT. However, current MMC methods ignore redundant information in the multimodal data. This indistinguishable redundant information hinders the mining of complementary information and thus reduces the performance of MMC. In this article, we propose a multimodal nonredundant clustering via sufficiency complementary mining that explores complementary information while maximizing the removal of redundant information. We first construct a multimodal autoencoding network to learn the single-modal and fusion representation of all modalities. Then, we design a sufficiency complementary mining (SCM) mechanism based on information theory to train this autoencoding network. SCM transforms the complementary information into the sufficiency of fusion representation for each modality while reconstructing the redundant information as a conditional mutual information between the fusion and each single-modal representation given original data. This ingenious design allows SCM to safely remove redundant information by minimizing this conditional mutual information under guaranteed sufficiency. Moreover, the clustering task and the multimodal autoencoding network are integrated into a unified framework to enable the learned complementary information to guide the clustering process. Extensive experimental results on eight large-scale real-world datasets show that our method outperforms the state-of-the-art MMC methods.

Deep multiview clustering (MVC) is to learn and utilize the rich relations across different views to enhance the clustering performance under a human-designed deep network. However, most existing deep MVCs meet two challenges. First, most current deep contrastive MVCs usually select the same instance across views as positive pairs and the remaining instances as negative pairs, which always leads to inaccurate contrastive learning (CL). Second, most deep MVCs only consider learning feature or cluster correlations across views, failing to explore the dual correlations. To tackle the above challenges, in this article, we propose a novel deep MVC framework by pseudo-label guided CL and dual correlation learning. Specifically, a novel pseudo-label guided CL mechanism is designed by using the pseudo-labels in each iteration to help removing false negative sample pairs, so that the CL for the feature distribution alignment can be more accurate, thus benefiting the discriminative feature learning. Different from most deep MVCs learning only one kind of correlation, we investigate both the feature and cluster correlations among views to discover the rich and comprehensive relations. Experiments on various datasets demonstrate the superiority of our method over many state-of-the-art compared deep MVCs. The source implementation code will be provided at https://github.com/ShizheHu/Deep-MVC-PGCL-DCL.

Multiview clustering (MVC) provides a natural formulation to generate clusters for multiview data, which is fundamental to lots of industrial tasks like autonomous driving, defect detection, and multisensor information fusion, as part of the foundation models. Most existing MVC methods suppose that the data of multiple views are available during the clustering process. However, that is a very strong assumption and is impractical when the views are incremental over time. In addition, if directly applying existing MVC approaches to the clustering setting with incremental views, the massive redundant information in each view might limit the knowledge sharing between historical and newly arrived views. To solve these problems, a continual information bottleneck (CIB) method is presented in this article, which addresses the incremental MVC issue by maximally preserving the consistency of a sequence of views and removing the redundant information in each view. In particular, to facilitate the knowledge transfer from historical views to incoming one, we build a knowledge library to store the representative samples in historical views. When adding a new view, we first construct a view-specific encoder with information-theoretic constraints to learn a compact and discriminative representation, in which redundant information in the new view is eliminated. Then, to capture the consistency information between historical views and the new view, a shared encoder is devised after retrieving the global neighbors in the library for the new view, which is performed by contrasting the cluster assignment and feature representation simultaneously. Finally, a unified objective function is devised to simultaneously optimize the knowledge library and clustering process, in which the knowledge library is updated by maximizing the mutual information between the new view and all historical ones to keep tracking knowledge about the earlier views. Extensive experiment on nine multiview benchmarks has verified the superiority of the CIB method over 19 baselines.

Multi-view action clustering leverages the complementary information from different camera views to enhance the clustering performance. Although existing approaches have achieved significant progress, they assume all camera views are available in advance, which is impractical when the camera view is incremental over time. Besides, learning the invariant information among multiple camera views is still a challenging issue, especially in continual learning scenario. Aiming at these problems, we propose a novel continual action clustering (CAC) method, which is capable of learning action categories in a continual learning manner. To be specific, we first devise a category memory library, which captures and stores the learned categories from historical views. Then, as a new camera view arrives, we only need to maintain a consensus partition matrix, which can be updated by leveraging the incoming new camera view rather than keeping all of them. Finally, a three-step alternate optimization is proposed, in which the category memory library and consensus partition matrix are optimized. The empirical experimental results on 6 realistic multi-view action collections demonstrate the excellent clustering performance and time/space efficiency of the CAC compared with 15 state-of-the-art baselines.

In recent several years, the information bottleneck (IB) principle provides an information-theoretic framework for deep multiview clustering (MVC) by compressing multi-view observations while preserving the relevant information of multiple views. Although existing IB-based deep MVC methods have achieved huge success, they rely on variational approximation and distribution assumption to estimate the lower bound of mutual information, which is a notoriously hard and impractical problem in high-dimensional multi-view spaces. In this work, we propose a new differentiable information bottleneck (DIB) method, which provides a deterministic and analytical MVC solution by fitting the mutual information without the necessity of variational approximation. Specifically, we first propose to directly fit the mutual information of high-dimensional spaces by leveraging normalized kernel Gram matrix, which does not require any auxiliary neural estimator to estimate the lower bound of mutual information. Then, based on the new mutual information measurement, a deterministic multi-view neural network with analytical gradients is explicitly trained to parameterize IB principle, which derives a deterministic compression of input variables from different views. Finally, a triplet consistency discovery mechanism is devised, which is capable of mining the feature consistency, cluster consistency and joint consistency based on the deterministic and compact representations. Extensive experimental results show the superiority of our DIB method on 6 benchmarks compared with 13 state-of-the-art baselines.

Contrastive multi-view clustering is widely recognized for its effectiveness in mining feature representation across views via contrastive learning (CL), gaining significant attention in recent years. Most existing methods mainly focus on the feature-level or/and cluster-level CL, but there are still two shortcomings. Firstly, feature-level CL is limited by the influence of anomalies and large noise data, resulting in insufficient mining of discriminative feature representation. Secondly, cluster-level CL lacks the guidance of global information and is always restricted by the local diversity information. We in this paper Learn dUal enhanCed rEpresentation for Contrastive Multi-view Clustering (LUCE-CMC) to effectively addresses the above challenges, and it mainly contains two parts, i.e., enhanced feature-level CL (En-FeaCL) and enhanced cluster-level CL (En-CluCL). Specifically, we first adopt a shared encoder to learn shared feature representations between multiple views and then obtain cluster-relevant information that is beneficial to the clustering results. Moreover, we design a reconstitution approach to force the model to concentrate on learning features that are critical to reconstructing the input data, reducing the impact of noisy data and maximizing the sufficient discriminative information of different views in helping the En-FeaCL part. Finally, instead of contrasting the view-specific clustering result like most existing methods do, we in the En-CluCL part make the information at the cluster-level more richer by contrasting the cluster assignment from each view and the cluster assignment obtained from the shared fused features. The end-to-end training methods of the proposed model are mutually reinforcing and beneficial. Extensive experiments conducted on multi-view datasets show that the proposed LUCE-CMC outperforms established baselines to a considerable extent. The source code is released at https://github.com/ShizheHu.

This survey is for the remembrance of one of the creators of the information bottleneck theory, Prof. Naftali Tishby, passing away at the age of 68 on August, 2021. Information bottleneck (IB), a novel information theoretic approach for pattern analysis and representation learning, has gained widespread popularity since its birth in 1999. It provides an elegant balance between data compression and information preservation, and improves its prediction or representation ability accordingly. This survey summarizes both the theoretical progress and practical applications on IB over the past 20-plus years, where its basic theory, optimization, extensive models and task-oriented algorithms are systematically explored. Existing IB methods are roughly divided into two parts: traditional and deep IB, where the former contains the IBs optimized by traditional machine learning analysis techniques without involving any neural networks, and the latter includes the IBs involving the interpretation, optimization and improvement of deep neural works (DNNs). Specifically, based on the technique taxonomy, traditional IBs are further classified into three categories: Basic, Informative and Propagating IB; While the deep IBs, based on the taxonomy of problem settings, contain Debate: Understanding DNNs with IB, Optimizing DNNs Using IB, and DNN-based IB methods. Furthermore, some potential issues deserving future research are discussed. This survey attempts to draw a more complete picture of IB, from which the subsequent studies can benefit.

Multitask image clustering approaches intend to improve the model accuracy on each task by exploring the relationships of multiple related image clustering tasks. However, most existing multitask clustering (MTC) approaches isolate the representation abstraction from the downstream clustering procedure, which makes the MTC models unable to perform unified optimization. In addition, the existing MTC relies on exploring the relevant information of multiple related tasks to discover their latent correlations while ignoring the irrelevant information between partially related tasks, which may also degrade the clustering performance. To tackle these issues, a multitask image clustering method named deep multitask information bottleneck (DMTIB) is devised, which aims at conducting multiple related image clustering by maximizing the relevant information of multiple tasks while minimizing the irrelevant information among them. Specifically, DMTIB consists of a main-net and multiple subnets to characterize the relationships across tasks and the correlations hidden in a single clustering task. Then, an information maximin discriminator is devised to maximize the mutual information (MI) measurement of positive samples and minimize the MI of negative ones, in which the positive and negative sample pairs are constructed by a high-confidence pseudo-graph. Finally, a unified loss function is devised for the optimization of task relatedness discovery and MTC simultaneously. Empirical comparisons on several benchmark datasets, NUS-WIDE, Pascal VOC, Caltech-256, CIFAR-100, and COCO, show that our DMTIB approach outperforms more than 20 single-task clustering and MTC approaches.

Aligning multiple heterogeneous modalities in a parameter-sharing encoder to mine consistent information is a core idea of multimodal learning. However, two drawbacks hinder the development of such methods for clustering tasks: (1) each modality contains a considerable amount of superfluous information that cannot be aligned, impeding the mining of consistent information; (2) one-to-one alignment is contradictory to the clustering principle of minimum intra-cluster distance, leading to suboptimal clustering results. In this paper, we propose a novel Consistency-Guided Multimodal Clustering method (ConGMC) to remove superfluous information within the modalities unsupervised through information theory while improving one-to-one alignment for the clustering task. ConGMC contains multiple unimodal encoders and a multimodal shared encoder, where the former learns unimodal representation while the latter aligns multiple modalities to learn the cluster partition. Specifically, we first construct a mutual information maximin function to distinguish consistent information from superfluous information, in which the consistent and superfluous information are maximally retained and removed, respectively. Then a Clustering-Friendly Alignment strategy (CF-Align) is designed to address the contradiction between the alignment and clustering tasks. CF-Align dynamically adjusts the set of negative samples according to the learned cluster partition to avoid increasing the intra-cluster distance. Finally, we consider the cluster partition as a consistent constraint to optimize the multimodal shared encoder, enabling consistent information to guide the training process iteratively. Moreover, a variational optimization algorithm is proposed to ensure that ConGMC converges to a local optimum. Numerous experimental results on twelve real-world datasets validate that the proposed ConGMC method outperforms the state-of-the-art multimodal clustering methods.

In many practical applications, massive data are observed from multiple sources, each of which contains multiple cohesive views, called hierarchical multiview (HMV) data, such as image-text objects with different types of visual and textual features. Naturally, the inclusion of source and view relationships offers a comprehensive view of the input HMV data and achieves an informative and correct clustering result. However, most existing multiview clustering (MVC) methods can only process single-source data with multiple views or multisource data with single type of feature, failing to consider all the views across multiple sources. Observing the rich closely related multivariate (i.e., source and view) information and the potential dynamic information flow interacting among them, in this article, a general hierarchical information propagation model is first built to address the above challenging problem. It describes the process from optimal feature subspace learning (OFSL) of each source to final clustering structure learning (CSL). Then, a novel self-guided method named propagating information bottleneck (PIB) is proposed to realize the model. It works in a circulating propagation fashion, so that the resulting clustering structure obtained from the last iteration can "self-guide" the OFSL of each source, and the learned subspaces are in turn used to conduct the subsequent CSL. We theoretically analyze the relationship between the cluster structures learned in the CSL phase and the preservation of relevant information propagated from the OFSL phase. Finally, a two-step alternating optimization method is carefully designed for optimization. Experimental results on various datasets show the superiority of the proposed PIB method over several state-of-the-art methods.

Cross-modal clustering (CMC) intends to improve the clustering accuracy (ACC) by exploiting the correlations across modalities. Although recent research has made impressive advances, it remains a challenge to sufficiently capture the correlations across modalities due to the high-dimensional nonlinear characteristics of individual modalities and the conflicts in heterogeneous modalities. In addition, the meaningless modality-private information in each modality might become dominant in the process of correlation mining, which also interferes with the clustering performance. To tackle these challenges, we devise a novel deep correlated information bottleneck (DCIB) method, which aims at exploring the correlation information between multiple modalities while eliminating the modality-private information in each modality in an end-to-end manner. Specifically, DCIB treats the CMC task as a two-stage data compression procedure, in which the modality-private information in each modality is eliminated under the guidance of the shared representation of multiple modalities. Meanwhile, the correlations between multiple modalities are preserved from the aspects of feature distributions and clustering assignments simultaneously. Finally, the objective of DCIB is formulated as an objective function based on a mutual information measurement, in which a variational optimization approach is proposed to ensure its convergence. Experimental results on four cross-modal datasets validate the superiority of the DCIB. Code is released at https://github.com/Xiaoqiang-Yan/DCIB.

Recommender systems aim at helping users to discover interesting items and assisting business owners to obtain more profits. Nonetheless, traditional recommendations fail to explore the varying importance of product characteristics for different product domains. In light of this, we propose a novel probabilistic model for recommendation, which could learn products’ characteristics in a fine-grained manner. Specifically, a user’s preference for a given product is modeled as a combination of visual and functional aspects. To make our method practical in large-scale industrial scenarios, we devise a computationally efficient learning algorithm to optimize VFPMF’s parameters. Experiments on four real-world datasets demonstrate the effectiveness and efficiency of our solution, compared with several state-of-the-art methods.

Abstract Recommender systems commonly encounter with the problems of data sparsity and cold start. Recently, social recommendation has emerged with the rapid expansion of social platforms, offering an opportunity to alleviate such two obstacles. Nevertheless, there are still two key limitations in existing studies. From the perspective of model design, previous social recommenders only consider the influence of a user's direct friends or uniformly treat the influences from different friends. From the perspective of model learning, most of them apply a sampling‐based optimization strategy, which requires high‐quality positive and negative samples. In light of the aforementioned limitations, we propose a new probabilistic method, named Graph Attentive Matrix Factorization (GAMF). Our method not only explicitly captures high‐order social relationships, but also adopts an attention mechanism to automatically pick up different influences between friends. Moreover, we develop an efficient optimization algorithm to learn model parameters in a non‐sampling manner. Extensive experiments on four large‐scale datasets show the superiority of GAMF over state‐of‐the‐art recommenders, especially under the cold start scenario.

The measurement of gene functional similarity plays a critical role in numerous biological applications, such as gene clustering, the construction of gene similarity networks. However, most existing approaches still rely heavily on traditional computational strategies, which are not guaranteed to achieve satisfactory performance. In this study, we propose a novel computational approach called GOGCN to measure gene functional similarity by modeling the Gene Ontology (GO) through Graph Convolutional Network (GCN). GOGCN is a graph-based approach that performs sufficient representation learning for terms and relations in the GO graph. First, GOGCN employs the GCN-based knowledge graph embedding (KGE) model to learn vector representations (i.e., embeddings) for all entities (i.e., terms). Second, GOGCN calculates the semantic similarity between two terms based on their corresponding vector representations. Finally, GOGCN estimates gene functional similarity by making use of the pair-wise strategy. During the representation learning period, GOGCN promotes semantic interaction between terms through GCN, thereby capturing the rich structural information of the GO graph. Further experimental results on various datasets suggest that GOGCN is superior to the other state-of-the-art approaches, which shows its reliability and effectiveness.

Modeling sequential behaviors is the core of sequential recommendation. As users visit items in chronological order, existing methods typically capture a user's present interests from his/her past-to-present behaviors, i.e., making recommendations with only the unidirectional past information. This article argues that future information is another critical factor for the sequential recommendation. However, directly learning from future-to-present behaviors inevitably causes data leakage. Here, it is pointed out that future information can be learned from users' collaborative behaviors. Toward this end, this article introduces sequential graphs to depict item transition relationships: where and how each item transits from and will transit to. This temporal evolution information is called the light cone in special and general relativity. Then, a bidirectional sequential graph convolutional network (BiSGCN) is proposed to learn item representations by encoding past and future light cones. Finally, a manifold translating embedding (MTE) method is proposed to model item transition patterns in Riemannian manifolds, which helps to better capture the geometric structures of light cones and item transition patterns. Experimental comparisons and ablation studies verify the outstanding performance of BiSGCN, the benefits of learning from the future, and the improvements of learning in Riemannian manifolds.

Next-item recommendation has been a hot research topic in academia and industry, which aims to help users discover the next interesting item. In this article, we propose a novel solution, namelygraph-augmented social translation model(GAST), which investigates the utility of dynamic social influence for the task of next-item recommendation. Specifically, we introduce a gated graph convolution module to better model long-term user preference. Furthermore, we design a cogating module to capture dynamic patterns at both sequential level and social level. In addition, a social-enhanced translation mechanism is devised to measure the intensity of user–item relationships. Extensive experiments under different recommendation scenarios demonstrate the rationality and effectiveness of our proposed GAST method over several state-of-the-art methods.

Next-item recommendation has been a hot research, which aims at predicting the next action by modeling users' behavior sequences. While previous efforts toward this task have been made in capturing complex item transition patterns, we argue that they still suffer from three limitations: 1) they have difficulty in explicitly capturing the impact of inherent order of item transition patterns; 2) only a simple and crude embedding is insufficient to yield satisfactory long-term users' representations from limited training sequences; and 3) they are incapable of dynamically integrating long-term and short-term user interest modeling. In this work, we propose a novel solution named graph-augmented capsule network (GCRec), which exploits sequential user behaviors in a more fine-grained manner. Specifically, we employ a linear graph convolution module to learn informative long-term representations of users. Furthermore, we devise a user-specific capsule module and a position-aware gating module, which are sensitive to the relative sequential order of the recently interacted items, to capture sequential patterns at union-level and point-level. To aggregate the long-term and short-term user interests as a representative vector, we design a dual-gating mechanism, which could decide the contribution ratio of each module given different contextual information. Through extensive experiments on four benchmarks, we validate the rationality and effectiveness of GCRec on the next-item recommendation task.

Generative adversarial nets (GANs) have enjoyed considerable success in computer vision and attracted much attention from recommender systems. However, due to the discrete nature of items, it is infeasible to graft GANs directly onto recommendation models. Although several methods have taken steps forward, their training processes are slow-convergent, time-consuming, or even unstable. This article proposes a novel framework named attentive adversarial collaborative filtering (AACF) and an efficient training strategy to improve GANs in recommender systems. There are two distinct novelties over previous work. First, AACF is a differentiable generative adversarial framework that introduces an attention mechanism and “virtual items” to bridge the gap between the generator and the discriminator. Owing to the intrinsic differentiability, AACF can be stably optimized with gradient descent methods. Second, the efficient training strategy substantially reduces computational complexity. It is capable of efficiently training and scaling up the AACF model to large datasets. Extensive experiments on various datasets demonstrate the effectiveness, fast convergence, stability, and scalability of AACF. Since our ideas are general in nature, they will open a path to stably and efficiently train GANs in the research areas with discrete data. The implementation code is available athttps://github.com/zhongchuansun/AACF.

A sequential recommendation has become a hot research topic, which seeks to predict the next interesting item for each user based on his action sequence. While previous methods have made many efforts to capture the dynamics of sequential patterns, we contend that they still suffer from two inherent limitations: 1) they fail to model item transition patterns in an efficient and time-sensitive manner and 2) they are unaware of the importance of dynamically capturing social influence, resulting in suboptimal performance. We introduce a new concept dubbed socio-sequential recommendation, where the challenge mainly lies in dynamically modeling social influences and capturing item-to-item transition patterns in a time-sensitive manner. In light of this, we contribute a novel solution named GCARec (short for graph-augmented co-attention model), which takes into account the joint effect of dynamic sequential patterns and dynamic social influences. GCARec decomposes socio-sequential recommendation workflow into two steps. First, we adopt a light graph embedding module to model long-term user preference. Then, we propose a time-sensitive attention mechanism and a social-aware attention mechanism to capture dynamic patterns at sequential-level and social-level, respectively. Extensive experiments have been conducted on eight real-world datasets from different scenarios, demonstrating the superiority of GCARec against several state-of-the-art methods. The codes and datasets have been released at:https://github.com/wubinzzu/GCARec.

With the fast-growing multi-modal/media data in the Big Data era, multi-view clustering (MVC) has attracted lots of attentions lately. Most MVCs focus on integrating and utilizing the complementary information among views by linear sum of the learned view weights and have shown great success in some fields. However, they fail to quantify how complementary the information across views actually utilized for benefiting final clustering. Additionally, most of them contain at least one parameter for regularization without prior knowledge, which puts pressure on the parameter-tuning and thus makes them impractical. In this paper, we propose a novel parameter-free multi-view information bottleneck (PMIB) clustering method to automatically identify and exploit useful complementary information among views, thus reducing the negative impact from the harmful views. Specifically, we first discover the informative view by measuring the relevant information preserved by the original data and the compact clusters with mutual information. Then, a new cross-view weight learning scheme is designed to learn how complementary between the informative view and remaining views. Finally, the quantitative correlations among views are fully exploited to improve the clustering performance without needing any additional parameters or prior knowledge. Experimental results on different kinds of multi-view datasets show the effectiveness of the proposed method.

MOTIVATION: Discovering the drug-target interactions (DTIs) is a crucial step in drug development such as the identification of drug side effects and drug repositioning. Since identifying DTIs by web-biological experiments is time-consuming and costly, many computational-based approaches have been proposed and have become an efficient manner to infer the potential interactions. Although extensive effort is invested to solve this task, the prediction accuracy still needs to be improved. More especially, heterogeneous network-based approaches do not fully consider the complex structure and rich semantic information in these heterogeneous networks. Therefore, it is still a challenge to predict DTIs efficiently. RESULTS: In this study, we develop a novel method via Multiview heterogeneous information network embedding with Hierarchical Attention mechanisms to discover potential Drug-Target Interactions (MHADTI). Firstly, MHADTI constructs different similarity networks for drugs and targets by utilizing their multisource information. Combined with the known DTI network, three drug-target heterogeneous information networks (HINs) with different views are established. Secondly, MHADTI learns embeddings of drugs and targets from multiview HINs with hierarchical attention mechanisms, which include the node-level, semantic-level and graph-level attentions. Lastly, MHADTI employs the multilayer perceptron to predict DTIs with the learned deep feature representations. The hierarchical attention mechanisms could fully consider the importance of nodes, meta-paths and graphs in learning the feature representations of drugs and targets, which makes their embeddings more comprehensively. Extensive experimental results demonstrate that MHADTI performs better than other SOTA prediction models. Moreover, analysis of prediction results for some interested drugs and targets further indicates that MHADTI has advantages in discovering DTIs. AVAILABILITY AND IMPLEMENTATION: https://github.com/pxystudy/MHADTI.

BACKGROUND: Recently, with the foundation and development of gene ontology (GO) resources, numerous works have been proposed to compute functional similarity of genes and achieved series of successes in some research fields. Focusing on the calculation of the information content (IC) of terms is the main idea of these methods, which is essential for measuring functional similarity of genes. However, most approaches have some deficiencies, especially when measuring the IC of both GO terms and their corresponding annotated term sets. To this end, measuring functional similarity of genes accurately is still challenging. RESULTS: In this article, we proposed a novel gene functional similarity calculation method, which especially encapsulates the specificity of terms and edges (STE). The proposed method mainly contains three steps. Firstly, a novel computing model is put forward to compute the IC of terms. This model has the ability to exploit the specific structural information of GO terms. Secondly, the IC of term sets are computed by capturing the genetic structure between the terms contained in the set. Lastly, we measure the gene functional similarity according to the IC overlap ratio of the corresponding annotated genes sets. The proposed method accurately measures the IC of not only GO terms but also the annotated term sets by leveraging the specificity of edges in the GO graph. CONCLUSIONS: We conduct experiments on gene functional classification in biological pathways, gene expression datasets, and protein-protein interaction datasets. Extensive experimental results show the better performances of our proposed STE against several baseline methods.

In the era of Internet of Things (IoT), intelligent recommendation is playing an important role in our daily life. How to provide personalized information to users is the core concern of Internet content service providers. To improve the recommendation quality, it is a hot topic to go beyond merely user–item interaction records and take social relations into account in IoT. Recently, emerged graph neural networks (GNNs) shine a light on simulating the recursive social diffusion process, to refine user embedding learning. Nevertheless, two key issues have not been well studied in previous studies: 1) they usually model user preference and social influence within a same semantic space and fail to simultaneously inject high-order connectivity information reflected in both user–item interaction graph and user–user social graph and 2) they typically rely on negative sampling to optimize a recommendation model, which makes them highly sensitive to the design of the sampler and hardly makes full use of GPU’s computing ability. In light of this, we propose a novel framework for item recommendation, namely, an efficient adaptive graph convolutional network (EAGCN). Specifically, we introduce a space-adaptive graph convolutional module, which could jointly explore the propagation process of user interest and social influence. Furthermore, a user-specific gating mechanism is designed to aggregate user representations from both spaces. To make EAGCN practical in social IoT, we devise a fast nonsampling leaner to optimize EAGCN’s parameters with better leveraging matrix computing of GPU. Extensive experiments under four scenarios show that our solution consistently and significantly outperforms strong baseline methods in both model effectiveness and training efficiency.

Multiview clustering (MVC) has recently been the focus of much attention due to its ability to partition data from multiple views via view correlations. However, most MVC methods only learn either interfeature correlations or intercluster correlations, which may lead to unsatisfactory clustering performance. To address this issue, we propose a novel dual-correlated multivariate information bottleneck (DMIB) method for MVC. DMIB is able to explore both interfeature correlations (the relationship among multiple distinct feature representations from different views) and intercluster correlations (the close agreement among clustering results obtained from individual views). For the former, we integrate both view-shared feature correlations discovered by learning a shared discriminative feature subspace and view-specific feature information to fully explore the interfeature correlation. This allows us to attain multiple reliable local clustering results of different views. Following this, we explore the intercluster correlations by learning the shared mutual information over different local clusterings for an improved global partition. By integrating both correlations, we formulate the problem as a unified information maximization function and further design a two-step method for optimization. Moreover, we theoretically prove the convergence of the proposed algorithm, and discuss the relationships between our method and several existing clustering paradigms. The experimental results on multiple datasets demonstrate the superiority of DMIB compared to several state-of-the-art clustering methods.

Weighted multi-view clustering (MVC) aims to combine the complementary information of multi-view data (such as image data with different types of features) in a weighted manner to obtain a consistent clustering result. However, when the cluster-wise weights across views are vastly different, most existing weighted MVC methods may fail to fully utilize the complementary information, because they are based on view-wise weight learning and can not learn the fine-grained cluster-wise weights. Additionally, extra parameters are needed for most of them to control the weight distribution sparsity or smoothness, which are hard to tune without prior knowledge. To address these issues, in this paper we propose a novel and effective Cluster-weighted mUlti-view infoRmation bottlEneck (CURE) clustering algorithm, which can automatically learn the cluster-wise weights to discover the discriminative clusters across multiple views and thus can enhance the clustering performance by properly exploiting the cluster-level complementary information. To learn the cluster-wise weights, we design a new weight learning scheme by exploring the relation between the mutual information of the joint distribution of a specific cluster (containing a group of data samples) and the weight of this cluster. Finally, a novel draw-and-merge method is presented to solve the optimization problem. Experimental results on various multi-view datasets show the superiority and effectiveness of our cluster-wise weighted CURE over several state-of-the-art methods.

An effective recommender system can significantly help customers to find desired products and assist business owners to earn more income. Nevertheless, the decision-making process of users is highly complex, not only dependent on the personality and preference of a user, but also complicated by the characteristics of a specific product. For example, for products of different domains (e.g., clothing versus office products), the product aspects that affect a user’s decision are very different. As such, traditional collaborative filtering methods that model only user-item interaction data would deliver unsatisfactory recommendation results. In this work, we focus on fine-grained modeling of product characteristics to improve recommendation quality. Specifically, we first divide a product’s characteristics into visual and functional aspects—i.e., thevisual appearanceandfunctionalityof the product. One insight is that, the visual characteristic is very important for products of visually-aware domain (e.g., clothing), while the functional characteristic plays a more crucial role for visually non-aware domain (e.g., office products). We then contribute a novel probabilistic model, namedVisual and Functional Probabilistic Matrix Factorization(VFPMF), to unify the two factors to estimate user preferences on products. Nevertheless, such an expressive model poses efficiency challenge in parameter learning from implicit feedback. To address the technical challenge, we devise a computationally efficient learning algorithm based on alternating least squares. Furthermore, we provide an online updating procedure of the algorithm, shedding some light on how to adapt our method to real-world recommendation scenario where data continuously streams in. Extensive experiments on four real-word datasets demonstrate the effectiveness of our method with both offline and online protocols.

Cross-modal clustering (CMC) aims to enhance the clustering performance by exploring complementary information from multiple modalities. However, the performances of existing CMC algorithms are still unsatisfactory due to the conflict of heterogeneous modalities and the high-dimensional non-linear property of individual modality. In this paper, a novel deep mutual information maximin (DMIM) method for cross-modal clustering is proposed to maximally preserve the shared information of multiple modalities while eliminating the superfluous information of individual modalities in an end-to-end manner. Specifically, a multi-modal shared encoder is firstly built to align the latent feature distributions by sharing parameters across modalities. Then, DMIM formulates the complementarity of multi-modalities representations as an mutual information maximin objective function, in which the shared information of multiple modalities and the superfluous information of individual modalities are identified by mutual information maximization and minimization respectively. To solve the DMIM objective function, we propose a variational optimization method to ensure it converge to a local optimal solution. Moreover, an auxiliary overclustering mechanism is employed to optimize the clustering structure by introducing more detailed clustering classes. Extensive experimental results demonstrate the superiority of DMIM method over the state-of-the-art cross-modal clustering methods on IAPR-TC12, ESP-Game, MIRFlickr and NUS-Wide datasets.

Abstract Simultaneous localization and mapping (SLAM) addresses the problem of constructing the map from noisy sensor data and tracking the robot's path within the built map. After decades of development, a lot of mature systems achieve competent results in feature‐based implementations. However, there are still problems when migrating the technology to practical applications. One typical example is the accuracy and robustness of SLAM in environment with illuminance and texture variations. To this end, two modules in the existing systems are improved here namely tracking and camera relocalization. In tracking module, image pyramid is processed with Laplacian of Gaussian (LoG) operator in feature extraction for enhanced edges and details. A majority voting mechanism is proposed to dynamically evaluate and redetermine the zero‐mean sum of square difference threshold according to the matching error estimation in patch search. In camera relocalization module, full convolutional neural network which focuses on certain parts of the input data is utilized in guiding for accurate output predictions. The authors implement the two modules into OpenvSLAM and propose a neural guided visual SLAM system named LoG‐SLAM. Experiments on publicly available datasets show that the accuracy and efficiency increase with LoG‐SLAM when compared with other feature‐based methods, and relocalization accuracy also improves compared with the recently proposed deep learning pipelines.

A novel semantic loop closure detection (SLCD) method is proposed in this article for visual simultaneous localization and mapping systems. SLCD aims to relieve the instance-level semantic inconsistency issue that arose from dynamic industrial scenes (e.g., autonomous driving in big cities). As the first step in this direction, SLCD fully exploits both low- and high-level video frame information, in a coarse-to-fine way. In SLCD, we adopt a convolutional neural network based object detection to acquire object information from the consecutive frames. Meanwhile, we perform a bag of visual words based similarity calculation to narrow the frames to coarse loop closure candidates. For these candidates, we perform an object matching on them to find their semantic inconsistency cases and remove involved semantic inconsistencies according to their cases. Then, we recalculate the similarity scores for these candidates. Finally, loop closures are determined by the similarity scores and a geometrical verification. Favorable performance of the proposed method is demonstrated by comparing it to other state-of-the-art methods using data from several public datasets and our new Dynamic Scenes dataset.

Traditional image clustering algorithms deal with single-task clustering (STC) problem on a single domain. However, with the increasing number of related images on the Web, it is challenging for STCs to perform related image clustering tasks independently without considering the between-task relationship, which mainly consists of similar visual features and image patterns among tasks. Therefore, it is intuitive to resort to multi-task clustering (MTC) algorithms. However, most existing MTCs learn a shared feature subspace, which may lead to negative transfer when facing the image clustering tasks that are not strongly related. In this paper, we propose a novel multi-task image clustering algorithm, which performs multiple image clustering tasks simultaneously and propagates the task correlation to improve clustering performance. Specifically, we first extend the information bottleneck method to cluster tasks independently. The related and unrelated images between the pairwise clusters of different tasks are then discovered. Meanwhile, two corresponding types of correlations are propagated among the tasks, where only the positive correlation benefits the clustering of each task. A sequential and collaborative method is further designed to ensure an optimal solution. Moreover, we perform a theoretical analysis of the properties on correlation propagation and the convergence of our algorithm. The experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art clustering methods.

In recent years, functional similarity has played an independent role in some biological fields such as gene clustering, gene functional prediction, and evaluation for protein-protein interaction. In this premise, some effective methods have already been proposed based on Gene Ontology (GO). Although these mainstream methods achieve the purpose for measuring gene functional similarity, they may have some deficiency when calculating the Information Content (IC) of GO terms. Consequently, measuring the functional similarity accurately is still a meaningful objective of research. In this paper, a novel method called SWE, is proposed for measuring gene functional similarity based on the GO graph. Firstly, an algorithm to measure terms' semantics based on their information in the GO graph is put forward. The information of GO terms mainly contains their depth, ancestors and descendants. Secondly, we calculate the IC of a term set by means of retrieving the inherited relationship between terms in a term set. Finally, the functional similarity between two genes is computed based on the IC overlap ratio of term sets annotating two genes respectively. Results demonstrate that SWE is superior to existing methods in some experiments such as functional classification of genes in a biological pathway, protein-protein interaction and gene expression experiment. Further analysis demonstrates that SWE takes not only the specificity of terms into account, but their information in the GO graph, both of which are shown to be consistent with human perspectives.

Image clustering has been one of the most important issues in the field of pattern recognition. However, most of existing methods only focus on utilizing either content or context information of images, failing to consider both of them. In fact, the powerful algorithms can be realized by a combination of the rich content and context information. This paper proposes a novel content-context information bottleneck (C2IB) algorithm, which simultaneously explores and exploits the content and context information for discovering image clusters. The "content" describes the intrinsic characteristics contained in each image such as the appearance feature, and the "context" depicts the close correlations between images such as inter-image distance or similarity. Then, we formulate the problem as an information loss function by maximally preserving the content and context information while compressing the images. Finally, we design a new sequential method for the optimization. Experimental results show the superiority of the proposed method.

Existing visual-textual cross-modal clustering techniques focus on finding a clustering partition of different modalities by dealing with each modality dependently or integrating multiple modalities into a shared space, which may results in unsatisfactory performance due to the heterogeneous gap of different modalities. Aiming at this problem, we propose a novel heterogeneous dual-task clustering (HDC) method, which is capable of exploring high-level relatedness between visual and textual data to improve the performance of individual task. Our intuition is that although the visual and textual data are heterogenous to each other, they may share related high-level semantics and rich latent correlations, which can lead to improved performance if we treat the clustering of visual and textual data as different but related learning tasks. Specifically, the problem of heterogeneous dual-task clustering is formulated as an information-theoretic function, in which the low-level information in each modality and high-level relatedness between multiple modalities are maximally preserved. Then, a progressive optimization method is proposed to ensure a local optimal solution. Extensive experiments show noticeable performance of the HDC approach in comparison with several state-of-the-art baselines.

Predicting what items a user will consume in the next time (i.e., next-item recommendation) is a crucial task for recommender systems. While the factorization method is a popular choice in recommendation, several recent efforts have shown that the inner product does not satisfy the triangle inequality, which may hurt the model's generalization ability. TransRec is a promising method to overcome this issue, which learns a distance metric to predict the strength of user-item interactions. Nevertheless, such method only uses the latest consumed item to model a user's short-term preference, which is insufficient for modeling fidelity. In this article, we propose a simple yet effective method named attentive translation model, to explicitly exploit high-order sequential information for next-item recommendation. Specifically, we construct a user-specific translation vector by accounting for multiple recent items, which encode more information about a user's short-term preference than the latest item. To aggregate multiple items into one representation, we devise a position-aware attention mechanism, learning different weights on items at different orders in a personalized way. Extensive experiments on four real-world datasets show that our method significantly outperforms several state-of-the-art methods.

Object categorization in images is fundamental to various industrial areas, such as automated visual inspection, fast image retrieval, and intelligent surveillance. Most existing methods treat visual features (e.g., scale-invariant feature transform) as content information of the objects, while regarding image tags as their contextual information. However, the image tags can hardly be acquired in completely unsupervised settings, especially when the image volume is too large to be marked. In this article, we propose a novel contextual multivariate information bottleneck (CMIB) method to conduct unsupervised image object categorization in multiple visual contexts. Unlike using manual contexts, the CMIB method first automatically generates a set of high-level basic clusterings by multiple global features, which are unprecedentedly defined as visual contexts since they can provide overall information about the target images. Then, the idea of the data compression procedure for object category discovery is proposed, in which the content and multiple visual contexts are maximally preserved through a “bottleneck.” Specifically, two Bayesian networks are initially built to characterize the relationship between data compression and information preservation. Finally, a novel sequential information-theoretic optimization is proposed to ensure the convergence of the CMIB objective function. Experimental results on seven real-world benchmark image datasets demonstrate that the CMIB method achieves better performance than the state-of-the-art baselines.

The widespread adoption of low-cost cameras generates massive amounts of videos recorded from different viewpoints every day. To cope with this vast amount of unlabeled and heterogeneous data, a new multi-task information bottleneck co-clustering (MIBC) approach is proposed to automatically categorize human actions in collections of unlabeled cross-view videos. Our motivation is that, if a learning action category from each view is seen as a single task, it is reasonable to assume that the tasks of learning action patterns from the videos recorded by multiple cameras are dependent and inter-related, since the actions of the same subjects synchronously recorded from different camera viewpoints are complementary to each other. MIBC aims to transfer the shared view knowledge across multiple tasks (i.e., camera viewpoints) to boost the performance of each task. Specifically, MIBC involves the following two parts: (1) extracting action categories for each task by independently maintaining its own relevant information, and (2) allowing the feature representations of all tasks to be compressed into a common feature space, which is utilized to capture the relatedness of multiple tasks and transfer the shared knowledge across different camera viewpoints. These two parts of MIBC work simultaneously and can be solved in a novel co-clustering mechanism. Our experimental evaluation on several cross-view action collections shows that the MIBC algorithm outperforms the existing state-of-the-art baselines.

Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks. However, their adaptations to crowd counting on single images are still in their infancy and suffer from severe over-fitting. Here we propose a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL). More specifically, we deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities. Our proposed method, named decorrelated ConvNet (D-ConvNet), is end-to-end-trainable and independent of the backbone fully-convolutional network architectures. Extensive experiments on very deep VGGNet as well as our customized network structure indicate the superiority of D-ConvNet when compared with several state-of-the-art methods. Our implementation will be released at https://github.com/shizenglin/Deep-NCL.

Deep convolutional networks (CNNs) reign undisputed as the new de-facto method for computer vision tasks owning to their success in visual recognition task on still images. However, their adaptations to crowd counting have not clearly established their superiority over shallow models. Existing CNNs turn out to be self-limiting in challenging scenarios such as camera illumination changing, partial occlusions, diverse crowd distributions, and perspective distortions for crowd counting because of their shallow structure. In this paper, we introduce a dynamic augmentation technique to train a much deeper CNN for crowd counting. In order to decrease overfitting caused by limited number of training samples, multitask learning is further employed to learn generalizable representations across similar domains. We also propose to aggregate multiscale convolutional features extracted from the entire image into a compact single vector representation amenable to efficient and accurate counting by way of “Vector of Locally Aggregated Descriptors” (VLAD). The “deeply supervised” strategy is employed to provide additional supervision signal for bottom layers for further performance improvement. Experimental results on three benchmark crowd datasets show that our method achieves better performance than the existing methods. Our implementation will be released at https://github.com/shizenglin/Multitask-Multiscale-Deep-NetVLAD.

Coherent motion detection remains a challenging problem due to the inherent complexity and vast diversity found in crowded scenes. Inspired by divide-and-conquer strategy, we desire to detect coherent motion from both local and global level. In this study, a novel collective density clustering (CDC) method is proposed to detect local and global coherent motion. We creatively define a collective density to discover underlying ordered density estimation, and subsequently a novel collective clustering algorithm is introduced, which is able to identify collective subgroups rapidly. Considering the complex interaction among subgroups, we present a hierarchical Union-Find-based collective merging algorithm to recognize coherent motion by merging collective subgroups. Our method is very efficient and effective. Experimental results on several challenging video datasets demonstrate that the proposed CDC achieves better results than state-of-the-art works, and multiple times or even tens of times faster. The proposed framework shows potential to be further applied to other problems (e.g., affine motion segmentation), related to local and global clustering.

Symbolic Aggregate approximation (SAX) has been the de facto standard representation methods for knowledge discovery in time series on a number of tasks and applications. So far, very little work has been done in empirically investigating the intrinsic properties and statistical mechanics in SAX w ords. In this paper, we applied several statistical measurements and proposed a new statistical measurement, i.e. information embedding cost (IEC) to analyze the statistical behaviors of the symbolic dynamics. Our experiments on the benchmark datasets and the clinical signals demonstrate that SAX can always reduce the complexity while preserving the core information embedded in the original time series with significant embedding efficiency, as well as robust to missing values and noise. Our proposed IEC score provide a priori to determine if SAX is adequate for specific dataset, which can be generalized to evaluate other symbolic representations. Our work provides an analytical framework with several statistical tools to analyze, evaluate and further improve the symbolic dynamics for knowledge discovery in time series.

Detecting coherent motion is significant for analysing the crowd motion in video applications. In this study, we propose the Collective Density Clustering(CDC) approach to recognize both local and global coherent motion having arbitrary shapes and varying densities. Firstly, the collective density is defined to reveal the underlying patterns with varying levels of density. Based on collective density, the collective clustering algorithm is further presented to recognize the local consistency, where density-based clustering is more adaptive to recognize clusters with arbitrary shapes. This algorithm has salient properties including single step of clustering process, automatical decision of clustering number and accurate identification of outliers. Finally, the collective merging algorithm is introduced to fully characterize the global consistency. Experiments on diverse crowd scenes, including pedestrians, traffic and bacterial colony, demonstrate the effectiveness for coherent motion detection. The comparisons show that our approach outperforms state-of-the-art coherent detection techniques.

Abstract This paper introduces a new crowd formation transform approach to achieve visually pleasing group formation transition and control. Its core idea is to transform crowd formation shapes with a least effort pair assignment using the Kuhn–Munkres algorithm, discover clusters of agent subgroups using affinity propagation and Delaunay triangulation algorithms and apply subgroup‐based social force model (SFM) to the agent subgroups to achieve alignment, cohesion and collision avoidance. Meanwhile, mutual information of the dynamic crowd is used to guide agents' movement at runtime. This approach combines both macroscopic (involving least effort position assignment and clustering) and microscopic (involving SFM) controls of the crowd transformation to maximally maintain subgroups' local stability and dynamic collective behaviour, while minimizing the overall effort (i.e. travelling distance) of the agents during the transformation. Through simulation experiments and comparisons, we demonstrate that this approach is efficient and effective to generate visually pleasing and smooth transformations and outperform several existing crowd simulation approaches including reciprocal velocity avoidances, optimal reciprocal collision avoidance and OpenSteer.

Class-imbalance is very common in real world. However, traditional state-of-the-art classifiers do not work well on imbalanced data sets for imbalanced class distribution. This paper considers imbalance learning from the viewpoint of ensemble pruning, and proposes a novel approach called IBEP (Inst ance-Based Ensemble Pruning) to improve classifier's performance on these data sets. Unlike traditional approaches which consider imbalance problem in training stage, IBEP focuses on the problem in prediction stage. Given an unlabeled instance, IBEP tries to search for the k nearest neighbors as the corresponding pruning set and adopts ensemble pruning strategy to select a subset of ensemble members to form sub-ensemble based on the pruning set to predict the instance. In this way, IBEP pays more attention to rare class and achieves better performance on imbalanced data set. Besides, two widely used sampling techniques, under-sampling and SMOTE, are skillfully combined with IBEP to further improve its performance. Experimental results on 14 data sets show that IBEP performs significantly better than many state-of-the-art classification methods on all metrics used in this paper including recall, f$-measure and g-mean.

This paper proposes a combination weighting algorithm using relative entropy for document clustering. Combination weighting is widely used in multiple attribute decision making (MADM) problem. However, there exist two difficulties to hinder the applications of combination weighting on document clustering. First, combination weighting is based on the integration of subjective weighting and objective weighting. However, there are so many attributes in documents that the subjective weights which rely on manual annotation by experts are impracticable. Secondly, a document data object might contain hundreds or even thousands of features. It is an extremely time-consuming task to calculate the combination weights. To address the issues, we suggest to simplify the combination weighting by not distinguishing subjective weight and objective weight. Meanwhile, we choose relative entropy method to reduce running time. In our algorithm, we obtain a combination weight set with 14 combination forms. The experiments on real document data show that both on the AC/PR/RE measures and the mutual information (MI) measure, the proposed CWRE-sIB algorithm is superior to the original sequential information bottleneck (sIB) algorithm and a series of weighting-sIB algorithms, which are built by applying a single weighting scheme to the original sIB algorithm.

ABSTRACT Most of existing traffic simulation efforts focus on urban regions with a coarse two‐dimensional representation; relatively few studies have been conducted to simulate realistic three‐dimensional traffic flows on a large, complex road web in rural scenes. In this paper, we present a novel agent‐based approach called accident‐avoidance full velocity difference model (abbreviated as AA‐FVDM) to simulate realistic street‐level rural traffics, on top of the existing FVDM. The main distinction between FVDM and AA‐FVDM is that FVDM cannot handle a critical real‐world traffic problem while AA‐FVDM settles this problem and retains the essence of FVDM. We also design a novel scheme to animate the lane‐changing maneuvering process (in particular, the execution course). Through numerous simulations, we demonstrate that besides addressing a previously unaddressed real‐world traffic problem, our AA‐FVDM method efficiently (in real time) simulates large‐scale traffic flows (tens of thousands of vehicles) with realistic, smooth effects. Furthermore, we validate our method using real‐world traffic data, and the validation results show that our method measurably outperforms state‐of‐the‐art traffic simulation methods.Copyright © 2013 John Wiley & Sons, Ltd.

Feature weighting is one of the popular and effective ways to improve clustering quality. How to choose a proper weighting method for a data object is widely recognized as a difficult problem. Among majority of weighting schemes and combination weigh

Proximal support vector machine (PSVM) is a simple but effective classifier, especially for solving large-scale data classification problems. An inherent deficiency of PSVM lies on its inefficiency for dealing with high-dimensional data. In this paper, we propose a parallel version of PSVM (PPSVM). Based on random dimensionality partitioning, PPSVM can obtain partitioned local model parameters in parallel, with combined parameters to form the final global solution. In fact, PPSVM enjoys two properties: 1) It can calculate model parameters in parallel and is therefore a fast learning method with theoretically proved convergence; and 2) It can avoid the inversion of large matrix, which makes it suitable for high-dimensional data. In the paper, we also propose a random PPSVM with randomly partitioned data in each iteration to improve the performance of PSVM. Experimental results on real-world data demonstrate that the proposed methods can obtain similar or even better prediction accuracy than PSVM with much better runtime efficiency.

In this paper, we propose a kind of extended fuzzy Petri net (EFPN) which is used in building the fault diagnosis model. First, we define a weighted mathematical expectation μ to calculate the distribution center of point-in-time with weight, and give the definition of weighted variance v to evaluate the indexes of discrete degree of the point-in-time with weight. Second, the maximum membership function ϕ and the fuzzy timestamp function τ are proposed, and these functions are used for calculating the temporal uncertainty and the different temporal distribution of TSSs. Finally, by using μ, v, ϕ and τ, the fault diagnosis model of substation equipments is constructed to analyze the confidence degree of all possible faults. Moreover, the repetitiveness of signals is analyzed to assess the influence degree caused by uncertainty factors which affect the results of reasoning. Simulation experiment shows that the EFPN is an effective substation fault diagnosis model, and it can be used to deal with the temporal uncertainty problem which is presented among the TSSs. More important is that the EFPN offers a new approach to make qualitative and quantitative analysis on the temporal relationship of the TSSs.

To analyze the composite fault in Discrete Event System (DES), a Probabilistic Petri net (PPN) and a fault diagnosis method for power system are proposed. Firstly, the PPN models are established on every fault spread direction. Secondly, the failed component is determined by the application of Petri net reasoning and probabilistic calculation. At last, the result is given by fusing all parties' results using mean method. Diagnosis analysis shows that the method can adapt to topology changes and obtain satisfying diagnosis results with incomplete information. In the PPN reasoning, calculating the fault probability of component is based on the prior probability from statistics, so the subjectivity of setting related parameters can be avoided.

Crowd transformation has been an important research field due to its diverse range of applications that include film production, computer games, robotics and performance training. We propose a novel approach with continuous space and continuous time for smooth crowd transformation. Most algorithms simulating the transformation of crowds focus on the trajectories of individual participants. As a contrast, the approach we proposed here focuses on the balanced assignment to maintain the collective behavior of the full crowd. We use a bitmap-based recognition of the starting and final formations and quantify the performance of the transformation with the mutual information. We demonstrate that our method is computationally efficient for several group sizes and formations.

Active learning traditionally assumes that labeled and unlabeled samples are subject to the same distributions and the goal of an active learner is to label the most informative unlabeled samples. In reality, situations may exist that we may not have unlabeled samples from the same domain as the labeled samples (i.e. target domain), whereas samples from auxiliary domains might be available. Under such situations, an interesting question is whether an active learner can actively label samples from auxiliary domains to benefit the target domain. In this paper, we propose a transfer active learning method, namely Transfer Active SVM (TrAcSVM), which uses a limited number of target instances to iteratively discover and label informative auxiliary instances. TrAcSVM employs an extended sigmoid function as instance weight updating approach to adjust the models for prediction of (newly arrived) target data. Experimental results on real-world data sets demonstrate that TrAcSVM obtains better efficiency and prediction accuracy than its peers.

We present a novel approach to automatically discover object categories from a collection of unlabeled images. This is achieved by the Information Bottleneck method, which finds the optimal partitioning of the image collection by maximally preserving the relevant information with respect to the latent semantic residing in the image contents. In this method, the images are modeled by the Bag-of-Words representation, which naturally transforms each image into a visual document composed of visual words. Then the sIB algorithm is adopted to learn the object patterns by maximizing the semantic correlations between the images and their constructive visual words. Extensive experimental results on 15 benchmark image datasets show that the Information Bottleneck method is a promising technique for discovering the hidden semantic of images, and is superior to the state-of-the-art unsupervised object category discovery methods.

Pursuing a moving target in modern computer games presents several challenges to situated agents, including real-time response, large-scale search space, severely limited computation resources, incomplete environmental knowledge, adversarial escaping strategy, and outsmarting the opponent. In this paper, we propose a novel tracking automatic optimization moving-target pursuit (TAO-MTP) algorithm employing improved tracking strategy to effectively address all challenges above for the problem involving single hunter and single prey. TAO-MTP uses a queue to store prey's trajectory, and simultaneously runs real-time adaptive A* (RTAA*) repeatedly to approach the optimal position updated periodically in the trajectory within limited steps, which makes the overall pursuit cost smallest. In the process, the hunter speculatively moves to any position explored in the trajectory, not necessarily the optimal position, to speed up convergence, and then directly moves along the trajectory to pursue the prey. Moreover, automatic optimization methods, such as reducing trajectory storage and optimizing pursuit path, are used to further enhance its performance. As long as the hunter's moving speed is faster than that of the prey, and its sense scope is large enough, it will eventually capture the prey. Experiments using commercial game maps show that TAO-MTP is independent of adversarial escaping strategy, and outperforms all the classic and state-of-the-art moving-target pursuit algorithms such as extended moving-target search (eMTS), path refinement moving-target search (PR MTS), moving-target adaptive A* (MTAA*), and generalized adaptive A* (GAA*).

This paper focuses on intelligent attributes of railway intelligent transportation system (RITS) to use agent-oriented G-net approach to construct the model about stations and trains in the simulation system based on multi-agent, which is called agent-oriented G-net train operation model (AGNTOM). The model integrates object-oriented approach, multi-agent technique and Petri nets analysis method, so it embodies the object-oriented concepts including class, inheritance, encapsulation, and utilizes existed Petri nets analysis tools to ensure the design of the simulation system. Furthermore, we use Petri nets theory in agent structure design and analysis phases to make multi-agent simulation system developing efficiently. Compared with existed models, AGNTOM has some prominent features including asynchronous message-passing, better description for the frame of the system, better autonomous decision-making and self-adjustment abilities.