Meta-learning for Bayesian optimization accelerates optimization by leveraging knowledge from previous tasks, but existing methods optimize for average performance and fail on challenging outlier tasks critical in practice. These limitations become particularly severe when target tasks exhibit distribution shifts or when optimization budgets are limited in real-world applications. We introduce MetaGameBO, a hierarchical game-theoretic framework that formulates meta-learning as robust optimization through CVaR-based task selection and diversity-aware sample learning. Our approach incorporates uncertainty-aware adaptation via probabilistic embeddings and Thompson sampling for robust generalization to out-of-distribution targets. We establish theoretical guarantees including convergence to game-theoretic equilibria and improved sample complexity, and demonstrate substantial improvements with 95.7% reduction in average loss and 88.6% lower tail risk compared to state-of-the-art methods on challenging tasks and distribution shifts.

Speech-driven 3D motion generation has garnered increasing research attention. However, it faces significant challenges in achieving style controllability, primarily due to the scarcity of motion style annotations. To address this, we propose a novel diffusion-based framework for co-speech holistic motion generation that enables example-based style control from videos. Our approach integrates hierarchical speech encoding with rhythm-aware denoising to produce natural and synchronized gestures and expressions. For effective style guidance, we introduce a contrastive style encoder that captures discriminative style representations from reference clips without explicit labeling, enabling generalization to motion styles unseen during training. Furthermore, we design a neural mapper that aligns 2D and 3D gesture features in a shared embedding space, facilitating direct style extraction from in-the-wild videos and seamless transfer to 3D motion. Extensive experiments and user studies show that our proposed approach achieves state-of-the-art performance in both qualitative and quantitative evaluations, offering a flexible solution for controllable motion generation.

Children with Autism Spectrum Disorder (ASD) often misunderstand social situations and struggle to participate in daily routines. Social Stories™ are traditionally crafted by psychology experts under strict constraints to address these challenges but are costly and limited in diversity. As Large Language Models (LLMs) advance, there's an opportunity to develop more automated, affordable, and accessible methods to generate Social Stories in real-time with broad coverage. However, adapting LLMs to meet the unique and strict constraints of Social Stories is a challenging issue. To this end, we propose SS-GEN, a Social Story GENeration framework with LLMs. Firstly, we develop a constraint-driven sophisticated strategy named StarSow to hierarchically prompt LLMs to generate Social Stories at scale, followed by rigorous human filtering to build a high-quality dataset. Additionally, we introduce quality assessment criteria to evaluate the effectiveness of these generated stories. Considering that powerful closed-source large models require very complex instructions and expensive API fees, we finally fine-tune smaller language models with our curated high-quality dataset, achieving comparable results at lower costs and with simpler instruction and deployment. This work marks a significant step in leveraging AI to personalize Social Stories cost-effectively for autistic children at scale, which we hope can encourage future research on special groups.

Yi Feng, Jiaqi Wang, Wenxuan Zhang, Zhuang Chen, Shen Yutong, Xiyao Xiao, Minlie Huang, Liping Jing, Jian Yu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Neural processes (NPs) are a promising paradigm to enable skill transfer learning across tasks with the aid of the distribution of functions. The previous NPs employ the empirical risk minimization principle in optimization. However, the fast adaption ability to different tasks can vary widely, and the worst fast adaptation can be catastrophic in risk-sensitive tasks. To achieve robust neural processes modeling, we consider the problem of training models in a risk-averse manner, which can control the worst fast adaption cases at a certain probabilistic level. By transferring the risk minimization problem to a two-level finite sum minimax optimization problem, we can easily solve it via a double-looped stochastic mirror prox algorithm with a task-aware variance reduction mechanism via sampling samples across all tasks. The mirror prox technique ensures better handling of complex constraint sets and non-Euclidean geometries, making the optimization adaptable to various tasks. The final solution, by aggregating prox points with the adaptive learning rates, enables a stable and high-quality output. The proposed learning strategy can work with various NPs flexibly and achieves less biased approximation with a theoretical guarantee. To illustrate the superiority of the proposed model, we perform experiments on both synthetic and real-world data, and the results demonstrate that our approach not only helps to achieve more accurate performance but also improves model robustness.

Existing work in physical-informed machine learning (PIML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical ordinary/partial differential equations (ODEs/PDEs) solvers. Of these, Neural Operators (NOs) have emerged as particularly promising. However, a key challenge in the field of NOs lies in developing methods that can effectively handle out-of-distribution (OOD) forecasting problems. Such problems involve the ability to adaptively learn from observations of the same dynamical system governed by ODEs/PDEs, where the underlying parameters are unknown and vary across instances. These tasks further require precise predictions even when faced with initial conditions and PDEs/ODEs parameters outside the training distribution. In this study, we consider the problem of training models in a risk-reverse manner. We introduce a risk-aware framework aimed at enhancing the OOD robustness of NOs by stochastically optimizing the conditional value-at-risk (CVAR) of a loss distribution. Through experiments on different distinct OOD tasks, our approach demonstrates a significant performance improvement over existing advanced NOs.

Predicting the interactions between compounds and their potential target proteins is crucial in drug discovery. Existing methods often assume that each compound has an adequate number of target proteins available for model training. However, in practice, the number of target proteins associated with compounds is often limited, making it difficult to gather a sufficient number of training examples. This results in learning bias in the model, leading to poor performance on these compounds. Moreover, this issue is evident in widely used datasets, such as GPCR and kinase, where 77.51% and 12.71% of compounds, respectively, have only one target protein available for model training. However, the issue has not been fully explored, presenting a challenge for model development. In this research, we propose CPOne, a framework designed to address the aforementioned issue. CPOne is a meta-learning based approach for compound-protein interaction prediction in one-shot scenario where each compound has only one target protein available for model training. By utilizing a meta compound learner, CPOne extracts the meta representation of compound from each task. Through fast gradient updates, this representation is quickly adapted to generate a compound-specific representation for the current task, thereby improving performance in one-shot scenario. Through comprehensive experiments, we empirically validate the superiority of CPOne, which demonstrates a promising performance improvement over established methods.

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing methods face challenges such as poor utilization of data or intricate training requirements. In this work, we found that the backdoor attack can construct an artificial bias similar to the model bias derived in standard training. Considering the strong adjustability of backdoor triggers, we are motivated to mitigate the model bias by carefully designing reverse artificial bias created from backdoor attack. Based on this, we propose a backdoor debiasing framework based on knowledge distillation, which effectively reduces the model bias from original data and minimizes security risks from the backdoor attack. The proposed solution is validated on both image and structured datasets, showing promising results. This work advances the understanding of backdoor attacks and highlights its potential for beneficial applications. The code for the study can be found athttps://github.com/KirinNg/DwB.

Recently, recommender system has achieved significant success. However, due to the openness of recommender systems, they remain vulnerable to malicious attacks. Additionally, natural noise in training data and issues such as data sparsity can also degrade the performance of recommender systems. Therefore, enhancing the robustness of recommender systems has become an increasingly important research topic. In this survey, we provide a comprehensive overview of the robustness of recommender systems. Based on our investigation, we categorize the robustness of recommender systems into adversarial robustness and non-adversarial robustness. In the adversarial robustness, we introduce the fundamental principles and classical methods of recommender system adversarial attacks and defenses. In the non-adversarial robustness, we analyze nonadversarial robustness from the perspectives of data sparsity, natural noise, and data imbalance. Additionally, we summarize commonly used datasets and evaluation metrics for evaluating the robustness of recommender systems. Finally, we also discuss the current challenges in the field of recommender system robustness and potential future research directions. Additionally, to facilitate fair and efficient evaluation of attack and defense methods in adversarial robustness, we propose an adversarial robustness evaluation library–ShillingREC, and we conduct evaluations of basic attack models and recommendation models. ShillingREC project is released at https://github.com/ chengleileilei/ShillingREC.

In extreme multi-label text classification (XMC), labels usually follow a long-tailed distribution, where most labels only contain a small number of documents and limit the performance of XMC. Data augmentation (DA) is a simple but effective strategy to solve such low-resource problems. In this paper, we propose a prompt-based DA method called XDA, which is specifically designed for XMC. First, we employ a soft prompt during the fine-tuning process of the T5 model for label-conditional DA, thereby enabling T5 to augment samples while preserving label-compatibility. Subsequently, XDA performs sample filtering on the augmented samples through the diversity of text and the consistency of labels, which enhances the quality of the DA. In contrast to traditional sample-level DA, we propose a pair-level DA method by masking the augmented sample-label pairs of head-labels during training, effectively mitigating the long-tailed problem. Comprehensive experiments on benchmark datasets have shown that the proposed XDA outperforms the state-of-the-art counterparts.

Target identification is one of the crucial tasks in drug research and development, as it aids in uncovering the action mechanism of herbs/drugs and discovering new therapeutic targets. Although multiple algorithms of herb target prediction have been proposed, due to the incompleteness of clinical knowledge and the limitation of unsupervised models, accurate identification for herb targets still faces huge challenges of data and models. To address this, we proposed a deep learning-based target prediction framework termed HTINet2, which designed three key modules, namely, traditional Chinese medicine (TCM) and clinical knowledge graph embedding, residual graph representation learning, and supervised target prediction. In the first module, we constructed a large-scale knowledge graph that covers the TCM properties and clinical treatment knowledge of herbs, and designed a component of deep knowledge embedding to learn the deep knowledge embedding of herbs and targets. In the remaining two modules, we designed a residual-like graph convolution network to capture the deep interactions among herbs and targets, and a Bayesian personalized ranking loss to conduct supervised training and target prediction. Finally, we designed comprehensive experiments, of which comparison with baselines indicated the excellent performance of HTINet2 (HR@10 increased by 122.7% and NDCG@10 by 35.7%), ablation experiments illustrated the positive effect of our designed modules of HTINet2, and case study demonstrated the reliability of the predicted targets of Artemisia annua and Coptis chinensis based on the knowledge base, literature, and molecular docking.

As an important branch of unsupervised learning methods, clustering makes a wide contribution in the area of data mining. It is well known that capturing the group-discriminative properties of each sample for clustering is crucial. Among them, deep clustering delivers promising results due to the strong representational power of neural networks. However, most of them adopt sample-level learning strategies, and the standalone data point barely captures its holistic cluster’s context and may undergo sub-optimal cluster assignment. To tackle this issue, we propose a Structure-driven Representation Learning (SRL) method by introducing latent structure information into the representation learning process at both the local and global levels. Specifically, a local-structure-driven sample representation strategy is proposed to approximate the estimation of data distribution, which models the neighborhood distribution of samples with potential structure information and exploits statistical dependencies between them to improve cluster consistency. A global-structure-driven cluster representation strategy is designed, where the context of each cluster is sufficiently encoded according to its samples (exemplar-theory) and corresponding prototype (prototype-theory). In this case, each cluster can only be related to its most similar samples, and different clusters are separated as much as possible. These two models are seamlessly combined into a joint optimization problem, which can be efficiently solved. Experiments on six widely-used datasets demonstrate the superiority of SRL over state-of-the-art clustering methods.

User preferences behind users' decision-making processes are highly diverse and may range from lower-level concepts with more specific intentions and higher-level concepts with more general intentions. In this case, user preferences tend to be expressed hierarchically. However, learning such intentions with different levels from user behaviors is challenging, and remains largely neglected by the existing literature. Meanwhile, user behavior data tends to be sparse because of the limited user response and the vast combinations of users and items, which results in cold-start problems with unclear user intentions. In this paper, we propose a mixture intention neural stochastic process (MINSP), a new view of the stochastic processes family using a general meta-learning mechanism and mixture strategy for robust recommendation with hierarchical preferences modeling. By considering the recommendation process for each user as a stochastic process, MINSP defines distributions over functions and is capable of rapid adaptation to different users. To capture the user's intention on different levels, an iterative additive algorithm is proposed that minimizes the approximation error by backfitting the residuals of previous approximations. In this case, the induced tree intention hierarchies serve as an aggregated structured representation of the whole preference, summarizing the gist for convenient navigation and better generalization. Furthermore, we theoretically analyze the generalization error bound of the proposed MINSP to guarantee the model performance. Empirical results show that our approach can achieve substantial improvement over the state-of-the-art baselines in terms of recommendation performance, and obtain an interpretable hierarchical intention structure.

ImageNet pre-training has enabled state-of-the-art results on many tasks. In spite of its recognized contribution to generalization, we observed in this study that ImageNet pre-training also transfers adversarial non-robustness from pre-trained model into fine-tuned model in the downstream classification tasks. We first conducted experiments on various datasets and network backbones to uncover the adversarial non-robustness in fine-tuned model. Further analysis was conducted on examining the learned knowledge of fine-tuned model and standard model, and revealed that the reason leading to the non-robustness is the non-robust features transferred from ImageNet pre-trained model. Finally, we analyzed the preference for feature learning of the pre-trained model, explored the factors influencing robustness, and introduced a simple robust ImageNet pre-training solution. Our code is available at https://github.com/jiamingzhang94/ImageNet-Pretraining-transfers-non-robustness.

Multi-label text classification (MLTC) involves tagging a document with its most relevant subset of labels from a label set. In real applications, labels usually follow a long-tailed distribution, where most labels (called as tail-label) only contain a small number of documents and limit the performance of MLTC. To facilitate this low-resource problem, researchers introduced a simple but effective strategy, data augmentation (DA). However, most existing DA approaches struggle in multi-label settings. The main reason is that the augmented documents for one label may inevitably influence the other co-occurring labels and further exaggerate the long-tailed problem. To mitigate this issue, we propose a new pair-level augmentation framework for MLTC, called Label-Specific Feature Augmentation (LSFA), which merely augments positive feature-label pairs for the tail-labels. LSFA contains two main parts. The first is for label-specific document representation learning in the high-level latent space, the second is for augmenting tail-label features in latent space by transferring the documents second-order statistics (intra-class semantic variations) from head labels to tail labels. At last, we design a new loss function for adjusting classifiers based on augmented datasets. The whole learning procedure can be effectively trained. Comprehensive experiments on benchmark datasets have shown that the proposed LSFA outperforms the state-of-the-art counterparts.

Unlike traditional statistical models depending on hand-specified priors, neural processes (NPs) have recently emerged as a class of powerful neural statistical models that combine the strengths of neural networks and stochastic processes. NPs can define a flexible class of stochastic processes well suited for highly non-trivial functions by encoding contextual knowledge into the function space. However, noisy context points introduce challenges to the algorithmic stability that small changes in training data may significantly change the models and yield lower generalization performance. In this paper, we provide theoretical guidelines for deriving stable solutions with high generalization by introducing the notion of algorithmic stability into NPs, which can be flexible to work with various NPs and achieves less biased approximation with theoretical guarantees. To illustrate the superiority of the proposed model, we perform experiments on both synthetic and real-world data, and the results demonstrate that our approach not only helps to achieve more accurate performance but also improves model robustness.

Discovering hidden pattern from imbalanced data is a critical issue in various real-world applications. Existing classification methods usually suffer from the limitation of data especially for minority classes, and result in unstable prediction and low performance. In this paper, a deep generative classifier is proposed to mitigate this issue via both model perturbation and data perturbation. Specially, the proposed generative classifier is derived from a deep latent variable model where two variables are involved. One variable is to capture the essential information of the original data, denoted as latent codes, which are represented by a probability distribution rather than a single fixed value. The learnt distribution aims to enforce the uncertainty of model and implement model perturbation, thus, lead to stable predictions. The other variable is a prior to latent codes so that the codes are restricted to lie on components in Gaussian Mixture Model. As a confounder affecting generative processes of data (feature/label), the latent variables are supposed to capture the discriminative latent distribution and implement data perturbation. Extensive experiments have been conducted on widely-used real imbalanced image datasets. Experimental results demonstrate the superiority of our proposed model by comparing with popular imbalanced classification baselines on imbalance classification task.

The traditional recommendation systems mainly use offline user data to train offline models, and then recommend items for online users, thus suffering from the unreliable estimation of user preferences based on sparse and noisy historical data. Conversational Recommendation System(CRS) uses the interactive form of the dialogue systems to solve the intrinsic problems of traditional recommendation systems. However, due to the lack of contextual information modeling, the existing CRS models are unable to deal with the exploitation and exploration(E&E) problem well, resulting in the heavy burden on users. To address the aforementioned issue, this work proposes a contextual information enhancement model tailored for CRS, called Knowledge Graph-enhanced Sampling(KGenSam). KGenSam integrates the dynamic graph of user interaction data with the external knowledge into one heterogeneous Knowledge Graph(KG) as the contextual information environment. Then, two samplers are designed to enhance knowledge by sampling fuzzy samples with high uncertainty for obtaining user preferences and reliable negative samples for updating recommender to achieve efficient acquisition of user preferences and model updating, and thus provide a powerful solution for CRS to deal with E&E problem. Experimental results on two real-world datasets demonstrate the superiority of KGenSam with significant improvements over state-of-the-art methods.

This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are more vulnerable to adversarial attacks; and (2) successful adversarial attacks lead to deviated and scattered activation map. Therefore, we use the mask method to design an attention-preserving loss and a contrast method to design a loss that makes the model’s attention rectification. Accordingly, an attention-based adversarial defense framework is designed, under which better adversarial training or stronger adversarial attacks can be performed through the above constraints. We hope the attention-related data analysis and defense solution in this study will shed some light on the mechanism behind the adversarial attack and also facilitate future adversarial defense/attack model design.

Synthesizing pseudo samples is currently the most effective way to solve the Generalized Zero Shot Learning (GZSL) problem. Most models achieve competitive performance but still suffer from two problems: (1) Feature confounding, the overall representations confound task-correlated and task-independent features, and existing models disentangle them in a generative way, but they are unreasonable to synthesize reliable pseudo samples with limited samples; (2) Distribution uncertainty, that massive data is needed when existing models synthesize samples from the uncertain distribution, which causes poor performance in limited samples of seen classes. In this paper, we propose a non-generative model to address these problems correspondingly in two modules: (1) Task-correlated feature disentanglement, to exclude the task-correlated features from task-independent ones by adversarial learning of domain adaption towards reasonable synthesis; (2) Controllable pseudo sample synthesis, to synthesize edge-pseudo and center-pseudo samples with certain characteristics towards more diversity generated and intuitive transfer. In addation, to describe the new scene that is the limit seen class samples in the training process, we further formulate a new ZSL task named the ‘Few-shot Seen class and Zero-shot Unseen class learning’ (FSZU). Extensive experiments on four benchmarks verify that the proposed method is competitive in the GZSL and the FSZU tasks.

The knowledge of phenotype-genotype associations is crucial for the understanding of disease mechanisms. Numerous studies have focused on developing efficient and accurate computing approaches to predict disease genes. However, owing to the sparseness and complexity of medical data, developing an efficient deep neural network model to identify disease genes remains a huge challenge. Therefore, we develop a novel deep neural network model that fuses the multi-view features of phenotypes and genotypes to identify disease genes (termed PDGNet). Our model integrated the multi-view features of diseases and genes and leveraged the feedback information of training samples to optimize the parameters of deep neural network and obtain the deep vector features of diseases and genes. The evaluation experiments on a large data set indicated that PDGNet obtained higher performance than the state-of-the-art method (precision and recall improved by 9.55 and 9.63 percent). The analysis results for the candidate genes indicated that the predicted genes have strong functional homogeneity and dense interactions with known genes. We validated the top predicted genes of Parkinson's disease based on external curated data and published medical literatures, which indicated that the candidate genes have a huge potential to guide the selection of causal genes in the 'wet experiment'. The source codes and the data of PDGNet are available at https://github.com/yangkuoone/PDGNet.

Video captioning is a joint task of computer vision and natural language processing, which aims to describe the video content using several natural language sentences. Nowadays, most methods cast this task as a mapping problem, which learns a mapping from visual features to natural language and generates captions directly from videos. However, the underlying challenge of video captioning,i.e., sequence to sequence mapping across the different domains, is still not well handled. To address these problems, we introduce the polishing mechanism in an attempt to mimic human polishing process and propose a generate-and-polish framework for video captioning. In this paper, we propose a two-step transformer based polishing network (TSTPN) consisting of two sub-modules: the generation-module is to generate the caption candidate and the polishing-module is to gradually refine the generated candidate. Specifically, the candidate provides a global information of the visual contents in a semantically-meaningful order, where it is firstly considered as a semantic intersnubber to bridge the semantic gap between the text and video, with the cross-modal attention mechanism for better cross-modal modeling; and it secondly provides a global planning ability to maintain the semantic consistency and fluency of the whole sentence for better sequence mapping. In experiments, we present adequate evaluations to show that the proposed TSTPN achieves the comparable and even better performance than the state-of-the-art methods on the benchmark datasets.

Social relations between users have been proven to be a good type of auxiliary information to improve the recommendation performance. However, it is a challenging issue to sufficiently exploit the social relations and correctly determine the user preference from both social and rating information. In this article, we propose a unified Bayesian Additive Matrix Approximation model (BAMA), which takes advantage of rating preference and social network to provide high-quality recommendation. The basic idea of BAMA is to extract social influence from social networks, integrate them to Bayesian additive co-clustering for effectively determining the user clusters and item clusters, and provide an accurate rating prediction. In addition, an efficient algorithm with collapsed Gibbs Sampling is designed to inference the proposed model. A series of experiments were conducted on six real-world social datasets. The results demonstrate the superiority of the proposed BAMA by comparing with the state-of-the-art methods from three views, all users, cold-start users, and users with few social relations. With the aid of social information, furthermore, BAMA has ability to provide the explainable recommendation.

The cold-start recommendation is an urgent problem in contemporary online applications. It aims to provide users whose behaviors are literally sparse with as accurate recommendations as possible. Many data-driven algorithms, such as the widely used matrix factorization, underperform because of data sparseness. This work adopts the idea of meta-learning to solve the user’s cold-start recommendation problem. We propose a meta-learning-based cold-start sequential recommendation framework called metaCSR, including three main components: Diffusion Representer for learning better user/item embedding through information diffusion on the interaction graph; Sequential Recommender for capturing temporal dependencies of behavior sequences; and Meta Learner for extracting and propagating transferable knowledge of prior users and learning a good initialization for new users. metaCSR holds the ability to learn the common patterns from regular users’ behaviors and optimize the initialization so that the model can quickly adapt to new users after one or a few gradient updates to achieve optimal performance. The extensive quantitative experiments on three widely used datasets show the remarkable performance of metaCSR in dealing with the user cold-start problem. Meanwhile, a series of qualitative analysis demonstrates that the proposed metaCSR has good generalization.

User preference modeling in recommendation system aims to improve customer experience through discovering users’ intrinsic preference based on prior user behavior data. This is a challenging issue because user preferences usually have complicated structure, such as inter-user preference similarity and intra-user preference diversity. Among them, inter-user similarity indicates different users may share similar preference, while intra-user diversity indicates one user may have several preferences. In literatures, deep generative models have been successfully applied in recommendation systems due to its flexibility on statistical distributions and strong ability for non-linear representation learning. However, they suffer from the simple generative process when handling complex user preferences. Meanwhile, the latent representations learned by deep generative models are usually entangled, and may range from observed-level ones that dominate the complex correlations between users, to latent-level ones that characterize a user’s preference, which makes the deep model hard to explain and unfriendly for recommendation. Thus, in this paper, we propose an Interpretable Deep Generative Recommendation Model (InDGRM) to characterize inter-user preference similarity and intra-user preference diversity, which will simultaneously disentangle the learned representation from observed-level and latent-level. In InDGRM, the observed-level disentanglement on users is achieved by modeling the user-cluster structure (i.e., inter-user preference similarity) in a rich multimodal space, so that users with similar preferences are assigned into the same cluster. The observed-level disentanglement on items is achieved by modeling the intra-user preference diversity in a prototype learning strategy, where different user intentions are captured by item groups (one group refers to one intention). To promote disentangled latent representations, InDGRM adopts structure and sparsity-inducing penalty and integrates them into the generative procedure, which has ability to enforce each latent factor focus on a limited subset of items (e.g., one item group) and benefit latent-level disentanglement. Meanwhile, it can be efficiently inferred by minimizing its penalized upper bound with the aid of local variational optimization technique. Theoretically, we analyze the generalization error bound of InDGRM to guarantee its performance. A series of experimental results on four widely-used benchmark datasets demonstrates the superiority of InDGRM on recommendation performance and interpretability.

Due to leveraging social relationships between users as well as their past social behavior, social recommendation becomes a core component in recommendation systems. Most existing social recommendation methods only consider direct social relationships among users (e.g., explicit and observed social relations). Recently, researchers proved that indirect social relationships can be effective to improve the recommendation quality when users only have few social connections, because it can identify the user interesting group even though the users have no observed social connection. In the literature, separate two-stage methods are studied, but they cannot explicitly capture the natural relationship between indirect social relations and latent user/item factors. In this paper, the main contribution is to propose a new joint recommendation model taking advantage of the Indirect Social Relations detection and Matrix Factorization collaborative filtering on social network and rating behavior information, which is called as InSRMF. In our work, the user latent factors can simultaneously and seamlessly capture user's personal preferences and social group characteristics. To optimize the InSRMF model, we develop a parallel graph vertex programming algorithm for efficiently handling large scale social recommendation data. Experiments based on four real-world datasets (Ciao, Epinions, Douban and Yelp) are conducted to demonstrate the performance of the proposed model. The experimental results have shown that InSRMF has ability to mine the proper indirect social relations and improve the recommendation performance compared with the testing methods in the literature, especially on the users with few social neighbors, Near-cold-start Users, Pure-cold-start Users and Long-tail Items.

The video captioning task aims to describe video content using several natural-language sentences. Although one-step encoder-decoder models have achieved promising progress, the generations always involve many errors, which are mainly caused by the large semantic gap between the visual domain and the language domain and by the difficulty in long-sequence generation. The underlying challenge of video captioning, i.e., sequence-to-sequence mapping across different domains, is still not well handled. Inspired by the proofreading procedure of human beings, the generated caption can be gradually polished to improve its quality. In this paper, we propose a deep reinforcement polishing network (DRPN) to refine the caption candidates, which consists of a word-denoising network (WDN) to revise word errors and a grammar-checking network (GCN) to revise grammar errors. On the one hand, the long-term reward in deep reinforcement learning benefits the long-sequence generation, which takes the global quality of caption sentences into account. On the other hand, the caption candidate can be considered a bridge between visual and language domains, where the semantic gap is gradually reduced with better candidates generated by repeated revisions. In experiments, we present adequate evaluations to show that the proposed DRPN achieves comparable and even better performance than the state-of-the-art methods. Furthermore, the DRPN is model-irrelevant and can be integrated into any video captioning models to refine their generated caption sentences.

Turing test was originally proposed to examine whether machine's behavior is indistinguishable from a human. The most popular and practical Turing test is CAPTCHA, which is to discriminate algorithm from human by offering recognition-alike questions. The recent development of deep learning has significantly advanced the capability of algorithm in solving CAPTCHA questions, forcing CAPTCHA designers to increase question complexity. Instead of designing questions difficult for both algorithm and human, this study attempts to employ the limitations of algorithm to design robust CAPTCHA questions easily solvable to human. Specifically, our data analysis observes that human and algorithm demonstrates different vulnerability to visual distortions: adversarial perturbation is significantly annoying to algorithm yet friendly to human. We are motivated to employ adversarially perturbed images for robust CAPTCHA design in the context of character-based questions. Four modules of multi-target attack, ensemble adversarial training, image preprocessing differentiable approximation, and expectation are proposed to address the characteristics of character-based CAPTCHA cracking. Qualitative and quantitative experimental results demonstrate the effectiveness of the proposed solution. We hope this study can lead to the discussions around adversarial attack/defense in CAPTCHA design and also inspire the future attempts in employing algorithm limitation for practical usage.

Deep generative model, especially variational auto-encoder (VAE), has been successfully employed by more and more recommendation systems. The reason is that it combines the flexibility of probabilistic generative model with the powerful non-linear feature representation ability of deep neural networks. The existing VAE-based recommendation models are usually proposed under global assumption by incorporating simple priors, e.g., a single Gaussian, to regularize the latent variables. This strategy, however, is ineffective when the user is simultaneously interested in different kinds of items, i.e., the user’s preference may be highly diverse. In this paper, thus, we propose a Deep Global and Local Generative Model for recommendation to consider both local and global structure among users (DGLGM) under the Wasserstein auto-encoder framework. Besides keeping the global structure like the existing model, DGLGM adopts a non-parametric Mixture Gaussian distribution with several components to capture the diversity of the users’ preferences. Each component is corresponding to one local structure and its optimal size can be determined via the automatic relevance determination technique. These two parts can be seamlessly integrated and enhance each other. The proposed DGLGM can be efficiently inferred by minimizing its penalized upper bound with the aid of local variational optimization technique. Meanwhile, we theoretically analyze its generalization error bounds to guarantee its performance in sparse feedback data with diversity. By comparing with the state-of-the-art methods, the experimental results demonstrate that DGLGM consistently benefits the recommendation system in top-N recommendation task.

Traffic flow analysis, prediction and management are keystones for building smart cities in the new era. With the help of deep neural networks and big traffic data, we can better understand the latent patterns hidden in the complex transportation networks. The dynamic of the traffic flow on one road not only depends on the sequential patterns in the temporal dimension but also relies on other roads in the spatial dimension. Although there are existing works on predicting the future traffic flow, the majority of them have certain limitations on modeling spatial and temporal dependencies. In this paper, we propose a novel spatial temporal graph neural network for traffic flow prediction, which can comprehensively capture spatial and temporal patterns. In particular, the framework offers a learnable positional attention mechanism to effectively aggregate information from adjacent roads. Meanwhile, it provides a sequential component to model the traffic flow dynamics which can exploit both local and global temporal dependencies. Experimental results on various real traffic datasets demonstrate the effectiveness of the proposed framework.

Human activity localization aims to recognize category labels and detect the spatio-temporal locations of activities in video sequences. Existing activity localization methods suffer from three major limitations. First, the search space is too large for three-dimensional (3D) activity localization, which requires the generation of a large number of proposals. Second, contextual relations are often ignored in these target-centered methods. Third, locating each frame independently fails to capture the temporal dynamics of human activity. To address the above issues, we propose a unified spatio-temporal deep Q-network (ST-DQN), consisting of a temporal Q-network and a spatial Q-network, to learn an optimized search strategy. Specifically, the spatial Q-network is a novel two-branch sequence-to-sequence deep Q-network, called TBSS-DQN. The network makes a sequence of decisions to search the bounding box for each frame simultaneously and accounts for temporal dependencies between neighboring frames. Additionally, the TBSS-DQN incorporates both the target branch and context branch to exploit contextual relations. The experimental results on the UCF-Sports, UCF-101, ActivityNet, JHMDB, and sub-JHMDB datasets demonstrate that our ST-DQN achieves promising localization performance with a very small number of proposals. The results also demonstrate that exploiting contextual information and temporal dependencies contributes to accurate detection of the spatio-temporal boundary.

Human activity localization aims at recognizing contents and detecting locations of activities in video sequences. With an increasing number of untrimmed video data, traditional activity localization methods always suffer from two major limitations. First, detailed annotations are needed in most existing methods, i.e., bounding-box annotations in every frame, which are both expensive and time consuming. Second, the search space is too large for 3D activity localization, which requires generating a large number of proposals. In this paper, we propose a unified deep Q-network with weak reward and weak loss (DWRLQN) to address the two problems. Certain weak knowledge and weak constraints involving the temporal dynamics of human activity are incorporated into a deep reinforcement learning framework under sparse spatial supervision, where we assume that only a portion of frames are annotated in each video sequence. Experiments on UCF-Sports, UCF-101 and sub-JHMDB demonstrate that our proposed model achieves promising performance by only utilizing a very small number of proposals. More importantly, our DWRLQN trained with partial annotations and weak information even outperforms fully supervised methods.

OBJECTIVE: This work investigates the possibility of automated malaria parasite detection in thick blood smears with smartphones. METHODS: We have developed the first deep learning method that can detect malaria parasites in thick blood smear images and can run on smartphones. Our method consists of two processing steps. First, we apply an intensity-based Iterative Global Minimum Screening (IGMS), which performs a fast screening of a thick smear image to find parasite candidates. Then, a customized Convolutional Neural Network (CNN) classifies each candidate as either parasite or background. Together with this paper, we make a dataset of 1819 thick smear images from 150 patients publicly available to the research community. We used this dataset to train and test our deep learning method, as described in this paper. RESULTS: A patient-level five-fold cross-evaluation demonstrates the effectiveness of the customized CNN model in discriminating between positive (parasitic) and negative image patches in terms of the following performance indicators: accuracy (93.46% ± 0.32%), AUC (98.39% ± 0.18%), sensitivity (92.59% ± 1.27%), specificity (94.33% ± 1.25%), precision (94.25% ± 1.13%), and negative predictive value (92.74% ± 1.09%). High correlation coefficients (>0.98) between automatically detected parasites and ground truth, on both image level and patient level, demonstrate the practicality of our method. CONCLUSION: Promising results are obtained for parasite detection in thick blood smears for a smartphone application using deep learning methods. SIGNIFICANCE: Automated parasite detection running on smartphones is a promising alternative to manual parasite counting for malaria diagnosis, especially in areas lacking experienced parasitologists.

Interpretability of recommender systems has caused increasing attention due to its promotion of the effectiveness and persuasiveness of recommendation decision, and thus user satisfaction. Most existing methods, such as Matrix Factorization (MF), tend to be black-box machine learning models that lack interpretability and do not provide a straightforward explanation for their outputs. In this paper, we focus on probabilistic factorization model and further assume the absence of any auxiliary information, such as item content or user review. We propose an influence mechanism to evaluate the importance of the users' historical data, so that the most related users and items can be selected to explain each predicted rating. The proposed method is thus called Influencebased Interpretable Recommendation model (In2Rec). To further enhance the recommendation accuracy, we address the important issue of missing not at random, i.e., missing ratings are not independent from the observed and other unobserved ratings, because users tend to only interact what they like. In2Rec models the generative process for both observed and missing data, and integrates the influence mechanism in a Bayesian graphical model. A learning algorithm capitalizing on iterated condition modes is proposed to tackle the non-convex optimization problem pertaining to maximum a posteriori estimation for In2Rec. A series of experiments on four real-world datasets (Movielens 10M, Netflix, Epinions, and Yelp) have been conducted. By comparing with the state-of-the-art recommendation methods, the experimental results have shown that In2Rec can consistently benefit the recommendation system in both rating prediction and ranking estimation tasks, and friendly interpret the recommendation results with the aid of the proposed influence mechanism.

The underlying challenge of human action prediction, i.e. maintaining prediction accuracy at very beginning of an action execution, is still not well handled. In this paper, we propose a Prediction Conditional Generative Adversarial Network (Prediction-CGAN) for predicting action, which shares information between completely observed and partially observed videos. Instead of generating future frames, we aim at completing visual representations of unfinished video, which can be directly utilized to predict action label no matter at any progress levels. The Prediction-CGAN incorporates the completion constraint to learn a transformation from incomplete actions to complete actions; the adversarial constraint to ensure the generation has similar discriminative power to complete representation; the label consistency constraint to encourage label consistency between each segment and its corresponding complete video; and the confidence monotonically increasing constraint to yield increasingly accurate predictions as observing more frames. Meanwhile, we introduce a novel adversarial criterion especially for prediction task, which requires the generation is more discriminative than its corresponding incomplete representation, while the generation is less discriminative than its real complete representation. In experiments, we present adequate evaluations to show that the proposed Prediction-CGAN outperforms state-of-the-art methods in action prediction.

Microblogging data contains a wealth of information of trending events and has gained increased attention among users, organizations, and research scholars for social media mining in different disciplines. Event storyline generation is one typical task of social media mining, whose goal is to extract the development stages with associated description of events. Existing storyline generation methods either generate storyline with less integrity or fail to guarantee the coherence between the discovered stages. Secondly, there are no scientific method to evaluate the quality of the storyline. In this paper, we propose a comprehensive storyline generation framework to address the above disadvantages. Given Microblogging data related to the specified event, we first propose Hot-Word-Based stage detection algorithm to identify the potential stages of event, which can effectively avoid ignoring important stages and preventing inconsistent sequence between stages. Community detection algorithm is applied then to select representative data for each stage. Finally, we conduct graph optimization algorithm to generate the logically coherent storylines of the event. We also introduce a new evaluation metric, SLEU, to emphasize the importance of the integrity and coherence of the generated storyline. Extensive experiments on real-world Chinese microblogging data demonstrate the effectiveness of the proposed methods in each module and the overall framework.

With the rapid development of Online Social Networks (OSNs), it is crucial to construct users' portraits from their dynamic behaviors to address the increasing needs for customized information services. Previous work on user attribute inference mainly concentrated on developing advanced features/models or exploiting external information and knowledge but ignored the contradiction between dynamic behaviors and stable demographic attributes, which results in deviation of user understanding

Recommender systems offer critical services in the age of mass information. Personalized ranking has been attractive both for content providers and customers due to its ability of creating a user-specific ranking on the item set. Although the powerful factor-analysis methods including latent factor models and deep neural network models have achieved promising results, they still suffer from the challenging issues, such as sparsity of recommendation data, uncertainty of optimization, and etc. To enhance the accuracy and generalization of recommender system, in this paper, we propose a deep generative ranking (DGR) model under the Wasserstein autoencoder framework. Specifically, DGR simultaneously generates the pointwise implicit feedback data (via a Beta-Bernoulli distribution) and creates the pairwise ranking list by sufficient exploiting both interacted and non-interacted items for each user. DGR can be efficiently inferred by minimizing its penalized evidence lower bound. Meanwhile, we theoretically analyze the generalization error bounds of DGR model to guarantee its performance in extremely sparse feedback data. A series of experiments on four large-scale datasets (Movielens (20M), Netflix, Epinions and Yelp in movie, product and business domains) have been conducted. By comparing with the state-of-the-art methods, the experimental results demonstrate that DGR consistently benefit the recommendation system in ranking estimation task, especially for the near-cold-start-users (with less than five interacted items).

Sentiment lexicon is a very important resource for opinion mining. Recently, many state-of-the-art works employ deep learning techniques to construct sentiment lexicons. In general, they firstly learn sentiment-aware word embeddings, and then use it as word features to construct sentiment lexicons. However, these methods do not consider the importance of each word to the distinguish of documents' sentiment polarities. As we know, most words among a document do not contribute to understand documents' semantic or sentiment. For example, in the tweet It's a good day, but i can't feel it. I'm really unhappy. The words `unhappy', `feel' and `can't' are much more important than the words `good', `day' in predicting the sentiment polarity of this twitter. Meanwhile, many words, such as `the', `in', `it' and `I'm' are uninformative. In this paper, we propose a novel sparse self-attention LSTM (SSALSTM) to efficiently capture the above intuitive facts, and then construct a large scale sentiment lexicons in twitter. In SSALSTM, we use a novel self-attention mechanism to capture the importance of each words to the distinguish of documents' sentiment polarities. In addition, a $L_1$ regularize is applied in the attentions which can ensure the sparsity characters that most words in a document are semantic and sentiment indistinguishable. Once we learn an efficient sentiment-aware word embedding, we train a classifier which uses sentiment-aware word embedding as features to predict the sentiment polarities of words. Extensive experiments on four publicly available datasets, SemEval 2013-2016, indicate that the sentiment lexicon generated by our proposed model achieves state-of-the-art performance on both supervised and unsupervised sentiment classification tasks.

In this paper, we propose a novel hierarchical supervision topic model to construct a topic-adaptive sentiment lexicon (TaSL) for higher-level classification tasks. It is widely recognized that sentiment lexicon as a useful prior knowledge is crucial in sentiment analysis or opinion mining. However, many existing sentiment lexicons are constructed ignoring the variability of the sentiment polarities of words in different topics or domains. For example, the word “amazing” can refer to causing great surprise or wonder but can also refer to very impressive and excellent. In TaSL, we solve this issue by jointly considering the topics and sentiments of words. Documents are represented by multiple pairs of topics and sentiments, where each pair is characterized by a multinomial distribution over words. Meanwhile, this generating process is supervised under hierarchical supervision information of documents and words. The main advantage of TaSL is that the sentiment polarity of each word in different topics can be sufficiently captured. This model is beneficial to construct a domain-specific sentiment lexicon and then effectively improve the performance of sentiment classification. Extensive experimental results on four publicly available datasets, MR, OMD, semEval13A, and semEval16B were presented to demonstrate the usefulness of the proposed approach. The results have shown that TaSL performs better than the existing manual sentiment lexicon (MPQA), the topic model based domain-specific lexicon (ssLDA), the expanded lexicons(Weka-ED, Weka-STS, NRC, Liu's), and deep neural network based lexicons (nnLexicon, HIT, HSSWE).

Attributed graphs have attracted much attention in recent years. Different from conventional graphs, attributed graphs involve two different types of heterogeneous information, i.e., structural information, which represents the links between the nodes, and attribute information on each of the nodes. Clustering on attributed graphs usually requires the fusion of both types of information in order to identify meaningful clusters. However, most of existing works implement the combination of these two types of information in a "global" manner by treating all nodes equally and learning a global weight for the information fusion. To address this issue, this paper proposed a novel weighted K -means algorithm with "local" learning for attributed graph clustering, called adaptive fusion of structural and attribute information (Adapt-SA) and analyzed the convergence property of the algorithm. The key advantage of this model is to automatically balance the structural connections and attribute information of each node to learn a fusion weight, and get densely connected clusters with high attribute semantic similarity. Experimental study of weights on both synthetic and real-world data sets showed that the weights learned by Adapt-SA were reasonable, and they reflected which one of these two types of information was more important to decide the membership of a node. We also compared Adapt-SA with the state-of-the-art algorithms on the real-world networks with varieties of characteristics. The experimental results demonstrated that our method outperformed the other algorithms in partitioning an attributed graph into a community structure or other general structures.

The discovery of disease-causing genes is a critical step towards understanding the nature of a disease and determining a possible cure for it. In recent years, many computational methods to identify disease genes have been proposed. However, making full use of disease-related (e.g., symptoms) and gene-related (e.g., gene ontology and protein-protein interactions) information to improve the performance of disease gene prediction is still an issue. Here, we develop a heterogeneous disease-gene-related network (HDGN) embedding representation framework for disease gene prediction (called HerGePred). Based on this framework, a low-dimensional vector representation (LVR) of the nodes in the HDGN can be obtained. Then, we propose two specific algorithms, namely, an LVR-based similarity prediction and a random walk with restart on a reconstructed heterogeneous disease-gene network (RW-RDGN), to predict disease genes with high performance. First, to validate the rationality of the framework, we analyze the similarity-based overlap distribution of disease pairs and design an experiment for disease-gene association recovery, the results of which revealed that the LVR of nodes performs well at preserving the local and global network structure of the HDGN. Then, we apply tenfold cross validation and external validation to compare our methods with other well-known disease gene prediction algorithms. The experimental results show that the RW-RDGN performs better than the state-of-the-art algorithm. The prediction results of disease candidate genes are essential for molecular mechanism investigation and experimental validation. The source codes of HerGePred and experimental data are available at https://github.com/yangkuoone/HerGePred.

Low-rank matrix approximation (LRMA) has attracted more and more attention in the community of recommendation. Even though LRMA-based recommendation methods (including Global LRMA and Local LRMA) obtain promising results, they suffer from the complicated structure of the large-scale and sparse rating matrix, especially when the underlying system includes a large set of items with various types and a huge amount of users with diverse interests. Thus, they have to predefine the important parameters, such as the rank of the rating matrix and the number of submatrices. Moreover, most existing Local LRMA methods are usually designed in a two-phase separated framework and do not consider the missing mechanisms of rating matrix. In this article, a non-parametric unified Bayesian graphical model is proposed for A daptive Lo cal low-rank M atrix A pproximation ( ALoMA ). ALoMA has ability to simultaneously identify rating submatrices, determine the optimal rank for each submatrix, and learn the submatrix-specific user/item latent factors. Meanwhile, the missing mechanism is adopted to characterize the whole rating matrix. These four parts are seamlessly integrated and enhance each other in a unified framework. Specifically, the user-item rating matrix is adaptively divided into proper number of submatrices in ALoMA by exploiting the Chinese Restaurant Process. For each submatrix, by considering both global/local structure information and missing mechanisms, the latent user/item factors are identified in an optimal latent space by adopting automatic relevance determination technique. We theoretically analyze the model’s generalization error bounds and give an approximation guarantee. Furthermore, an efficient Gibbs sampling-based algorithm is designed to infer the proposed model. A series of experiments have been conducted on six real-world datasets ( Epinions , Douban , Dianping , Yelp , Movielens (10M), and Netflix ). The results demonstrate that ALoMA outperforms the state-of-the-art LRMA-based methods and can easily provide interpretable recommendation results.

Review has been proven to be an important information in recommendation. Different from the overall user-item rating matrix, it can provide textual information that exhibits why a user likes an item or not. Recently, more and more researchers have paid attention on review-based rating prediction. There are two challenging issues: how to extract representative features to characterize users / items from reviews and how to leverage them for recommendation system. In this paper, we propose a Neural Gaussian Mixture Model (NGMM) for review-based rating prediction task. Among it, the review textual information is used to construct two parallel neural networks for users and items respectively, so that the users' preferences and items' properties can be sufficiently extracted and represented as two latent vectors. A shared layer is introduced on the top to couple these two networks together and model user-item rating based on the features learned from reviews. Specifically, each rating is modeled via a Gaussian mixture model, where each Gaussian component has zero variance, the mean described by the corresponding component in user's latent vector and the weight indicated by the corresponding component in item's latent vector. Extensive experiments are conducted on five real-world Amazon review datasets. The experimental results have demonstrated that our proposed NGMM model achieves the state-of-the-art performance in review-based rating prediction task.

Objective: Investigating the molecular mechanisms of symptoms is a vital task in precision medicine to refine disease taxonomy and improve the personalized management of chronic diseases. Although there are abundant experimental studies and computational efforts to obtain the candidate genes of diseases, the identification of symptom genes is rarely addressed. We curated a high-quality benchmark dataset of symptom-gene associations and proposed a heterogeneous network embedding for identifying symptom genes. Methods: We proposed a heterogeneous network embedding representation algorithm, which constructed a heterogeneous symptom-related network that integrated symptom-related associations and applied an embedding representation algorithm to obtain the low-dimensional vector representation of nodes. By measuring the relevance between symptoms and genes via calculating the similarities of their vectors, the candidate genes of given symptoms can be obtained. Results: A benchmark dataset of 18 270 symptom-gene associations between 505 symptoms and 4549 genes was curated. We compared our method to baseline algorithms (FSGER and PRINCE). The experimental results indicated our algorithm achieved a significant improvement over the state-of-the-art method, with precision and recall improved by 66.80% (0.844 vs 0.506) and 53.96% (0.311 vs 0.202), respectively, for TOP@3 and association precision improved by 37.71% (0.723 vs 0.525) over the PRINCE. Conclusions: The experimental validation of the algorithms and the literature validation of typical symptoms indicated our method achieved excellent performance. Hence, we curated a prediction dataset of 17 479 symptom-candidate genes. The benchmark and prediction datasets have the potential to promote investigations of the molecular mechanisms of symptoms and provide candidate genes for validation in experimental settings.

In the real-world environments, multipath components (MPCs) of wireless channels are generally distributed as groups, i.e., clusters. Modeling the clustered MPCs is important and necessary for channel modeling and an automatic clustering algorithm is thus required. This paper proposes a novel Kernel-power-density (KPD) based algorithm for MPC clustering. It uses the Kernel density to incorporate the modeled behavior of MPCs and takes into account the power of the MPCs. The proposed algorithm only considers the K nearest MPCs in the density estimation to better identify the local density variations of MPCs. Simulations validate the KPD algorithm and almost no performance degradation is found even with a large number of clusters and large cluster angular spread. The KPD algorithm enables applications with no prior knowledge about the clusters such as number and initial locations. It can be used for the cluster based channel modeling for 4G#x002F;5G communications.

Multi-label problems arise in various domains, including automatic multimedia data categorization, and have generated significant interest in computer vision and machine learning community. However, existing methods do not adequately address two key challenges: exploiting correlations between labels and making up for the lack of labelled data or even missing labelled data. In this paper, we proposed to use a semi-supervised singular value decomposition (SVD) to handle these two challenges. The proposed model takes advantage of the nuclear norm regularization on the SVD to effectively capture the label correlations. Meanwhile, it introduces manifold regularization on mapping to capture the intrinsic structure among data, which provides a good way to reduce the required labelled data with improving the classification performance. Furthermore, we designed an efficient algorithm to solve the proposed model based on the alternating direction method of multipliers, and thus, it can efficiently deal with large-scale data sets. Experimental results for synthetic and real-world multimedia data sets demonstrate that the proposed method can exploit the label correlations and obtain promising and better label prediction results than the state-of-the-art methods.

In most of existing digital cameras, color images have to be reconstructed from raw images which only have one color sensed at each pixel, as their imaging sensors are covered by color filter arrays (CFAs). At each pixel a CFA usually allows only a portion of the light spectrum to pass through and thereby reduces the light sensitivity of pixels. To address this issue, previous works have explored adding panchromatic pixels into CFAs. However, almost all existing methods assign panchromatic pixels empirically, making the designed CFAs prone to aliasing artifacts. In this paper, based on a mathematical model we propose a fully automatic approach to designing high-sensitivity CFAs using panchromatic pixels. By the frequency structure representation of CFAs, we formulate high-sensitivity CFA design as a continuous multi-objective optimization problem, where robustness to aliasing artifacts and percentage of panchromatic pixels are simultaneously maximized. We analyze the characteristics of our new formulation. According to the analysis, we develop a new method to propose frequency structure candidates, which can produce CFAs that reach a desired percentage of panchromatic pixels. Then for each candidate, we optimize parameters to obtain the final CFA, which is an appropriately balanced solution to the multi-objective optimization problem. We formulate the two design procedures as constrained optimization problems and solve them using the alternating direction method (ADM). Extensive experiments confirm the advantage of the proposed method in both low-light and normal-light conditions.

Demosaicking is the problem of reconstructing a color image from the raw image captured by a digital color camera that covers its only imaging sensor with a color filter array (CFA). Sparse representation-based demosaicking has been shown to produce superior reconstruction quality. However, almost all existing algorithms in this category use the CFAs, which are not specifically optimized for the algorithms. In this paper, we consider optimally designing CFAs for sparse representation-based demosaicking, where the dictionary is well-chosen. The fact that CFAs correspond to the projection matrices used in compressed sensing inspires us to optimize CFAs via minimizing the mutual coherence. This is more challenging than that for traditional projection matrices because CFAs have physical realizability constraints. However, most of the existing methods for minimizing the mutual coherence require that the projection matrices should be unconstrained, making them inapplicable for designing CFAs. We consider directly minimizing the mutual coherence with the CFA's physical realizability constraints as a generalized fractional programming problem, which needs to find sufficiently accurate solutions to a sequence of nonconvex nonsmooth minimization problems. We adapt the redistributed proximal bundle method to address this issue. Experiments on benchmark images testify to the superiority of the proposed method. In particular, we show that a simple sparse representation-based demosaicking algorithm with our specifically optimized CFA can outperform LSSC [1]. To the best of our knowledge, it is the first sparse representation-based demosaicking algorithm that beats LSSC in terms of CPSNR.

Cluster-based channel modeling has been an important trend in the development of channel model, as it maintains accuracy while reducing complexity. Whereas a large number of channel measurements have shown that multipath components (MPCs) are distributed as groups, i.e., clusters, existing clustering algorithms have various drawbacks with respect to complexity, threshold choices, and/or assumptions about prior knowledge. In this paper, a kernel-power-density (KPD)-based algorithm is proposed for MPC clustering. It uses the kernel density of MPCs to incorporate the modeled behavior of MPCs and takes into account the power of the MPCs. Furthermore, the KPD algorithm only considers the K nearest MPCs in the density estimation to better identify the local density variations of MPCs. A heuristic approach of cluster merging is used to improve the performance. Both simulation and channel measurements validate the KPD algorithm, and almost no performance degradation is found even with a large number of clusters and large cluster angular spread, which outperforming other algorithms. The KPD algorithm enables applications in multipleinput-multiple-output channels with no prior knowledge about the clusters, such as number and initial locations. It also has a fairly low computational complexity and can be used for clusterbased channel modeling.

In this paper, we propose a novel channel impulse response (CIR) clustering algorithm using a sparsity-based method, which exploits the feature of CIR that power of multipath component (MPC) is exponentially decreasing with increasing delay. We first use a sparsity-based optimization to recover CIRs, which can be well solved by using reweighted ℓ1minimization. Then a heuristic approach is provided to identify clusters in the recovered CIRs, which leads to improved clustering accuracy in comparison to identifying clusters directly in the raw CIRs. The proposed algorithm incorporates the physical behaviors of MPCs into the clustering framework and enables applications with no prior knowledge of the clusters, such as number and initial locations of clusters. The results in this paper can be used to parameterize the CIR model of radio channels.

In digital color imaging, the raw image is typically obtained through a single sensor covered by a color filter array (CFA), which allows only one color component to be measured at each pixel. The procedure to reconstruct a full color image from the raw image is known as demosaicking. Since the CFA may cause irreversible visual artifacts, the CFA and the demosaicking algorithm are crucial to the quality of demosaicked images. Fortunately, the design of CFAs in the frequency domain provides a theoretical approach to handling this issue. However, almost all the existing design methods in the frequency domain involve considerable human effort. In this paper, we present a new method to automatically design CFAs in the frequency domain. Our method is based on the frequency structure representation of mosaicked images. We utilize a multi-objective optimization approach to propose frequency structure candidates, in which the overlap among the frequency components of images mosaicked with the CFA is minimized. Then, we optimize parameters for each candidate, which is formulated as a constrained optimization problem. We use the alternating direction method to solve it. Our parameter optimization method is applicable to arbitrary frequency structures, including those with conjugate replicas of chrominance components. Experiments on benchmark images confirm the advantage of the proposed method.

One of the main research problems in heterogeneous transfer learning is to determine whether a given source domain is effective in transferring knowledge to a target domain, and then to determine how much of the knowledge should be transferred from a source domain to a target domain. The main objective of this paper is to solve this problem by evaluating the relatedness among given domains through transferred weights. We propose a novel method to learn such transferred weights with the aid of co-occurrence data, which contain the same set of instances but in different feature spaces. Because instances with the same category should have similar features, our method is to compute their principal components in each feature space such that co-occurrence data can be rerepresented by these principal components. The principal component coefficients from different feature spaces for the same instance in the co-occurrence data have the same order of significance for describing the category information. By using these principal component coefficients, the Markov Chain Monte Carlo method is employed to construct a directed cyclic network where each node is a domain and each edge weight is the conditional dependence from one domain to another domain. Here, the edge weight of the network can be employed as the transferred weight from a source domain to a target domain. The weight values can be taken as a prior for setting parameters in the existing heterogeneous transfer learning methods to control the amount of knowledge transferred from a source domain to a target domain. The experimental results on synthetic and real-world data sets are reported to illustrate the effectiveness of the proposed method that can capture strong or weak relations among feature spaces, and enhance the learning performance of heterogeneous transfer learning.

Multi-label problems arise in various domains including automatic multimedia data categorization, and have generated significant interest in computer vision and machine learning community. However, existing methods do not adequately address two key challenges: exploiting correlations between labels and making up for the lack of labeled data or even missing labels. In this paper, we proposed a semi-supervised low-rank mapping (SLRM) model to handle these two challenges. SLRM model takes advantage of the nuclear norm regularization on mapping to effectively capture the label correlations. Meanwhile, it introduces manifold regularizer on mapping to capture the intrinsic structure among data, which provides a good way to reduce the required labeled data with improving the classification performance. Furthermore, we designed an efficient algorithm to solve SLRM model based on alternating direction method of multipliers and thus it can efficiently deal with large-scale datasets. Experiments on four real-world multimedia datasets demonstrate that the proposed method can exploit the label correlations and obtain promising and better label prediction results than state-of-the-art methods.

In fuzzy clustering, the fuzzy c-means (FCM) is the most known algorithm. Several extensions and variations of FCM had been proposed in the literature. The first important extension to FCM was proposed by Gustafson and Kessel (GK). In the GK fuzzy clustering, they considered the effect of different cluster shapes except for spherical shapes by replacing the Euclidean distance of the FCM objective function with the Mahalanobis distance. The GK algorithm has become one of the most frequently used clustering algorithms. Just like FCM, the fuzziness index m is a parameter in which the value will greatly influence the performance of the GK algorithm. However, there is no theoretical work on the parameter selection for the fuzziness index m of GK. In this paper, we reveal the relation between the stable fixed points of the GK algorithm and the datasets using Jacobian matrix analysis, and then provide a theoretical base for selecting the fuzziness index m in the GK algorithm. Some experimental results verify the effectiveness of our theoretical results.

The Penrose pixel layout, an aperiodic pixel layout in rhombus Penrose tiling, has been shown to substantially outperform the existing square pixel layout in super-resolution. However, it was tested only on grayscale images. To study its performance on color images, we have to reconstruct regular color images from Penrose raw images, i.e., images with only one color component at each Penrose pixel, resulting in the problem of demosaicking from Penrose pixels. Penrose demosaicking is more difficult than regular demosaicking, because none of the color components of the reconstructed regular color images are available. Therefore, most of the traditional demosaicking methods do not apply. We develop a sparse representation-based method for Penrose demosaicking. Extensive experiments show that Penrose pixel layout outperforms regular pixel layouts in terms of both perceptual evaluation and S-CIELAB. The Penrose pixel layout is unique among all irregular layouts because it is uniformly three-colorable and it has only two pixel shapes, thick and thin rhombi, making its manufacturing relatively easy.

Within the bag‐of‐words (BOWs) framework, the multiple cues fusion methods provide excellent results in object and scene classification. Top‐down colour attention (CA) method is developed to use colour to guide attention by means of a top‐down category‐specific attention map. In this method, more features are taken from category‐specific colour regions where objects are more likely to be contained. In CA, the colours on the object are considered separately, so the diversity of object colours and large intra‐class colour variation make the discrimination of every colour on the object different. Object could be recognised as a collection of related colours. To enhance the object recognition capability of CA, our colour combination attention method uses mutual information and the colour combination histogram to estimate and combine the colours on the object. Results are presented on three challenging data sets, and the experiments demonstrate that the proposed feature fusion method significantly outperforms the state‐of‐the‐art methods.

Symptoms and signs (symptoms in brief) are the essential clinical manifestations for traditional Chinese medicine (TCM) diagnosis and treatments. To gain insights into the molecular mechanism of symptoms, this paper presents a network-based data mining method to integrate multiple phenotype-genotype data sources and predict the prioritizing gene rank list of symptoms. The result of this pilot study suggested some insights on the molecular mechanism of symptoms.

Frequent itemsets mining is often used to find medication law from dataset of Chinese herb prescriptions. Threshold of support count is difficult to set for traditional algorithm of frequent itemsets mining. In the meantime, the number of frequent itemsets is always so big that the result is hard to understand. Some algorithms were proposed to find significant and redundant-aware itemsets. However, the itemsets obtained could not reflect all the information in the dataset. In this paper, a new method was proposed to obtain a collection of itemsets which had the feature of significant, redundant-aware and comprehensive. Firstly, closed frequent itemsets were mined from the dataset of Chinese herbs prescriptions using CHARM algorithm. Then, the itemsets were compressed by FICMC (Frequent Itemsets Compressing based on Minimum Cover) algorithm. Medication law of Chinese herbs could be fully mined from the dataset using this method.

Patch-level features are essential for achieving good performance in compute vision tasks. Besides well-known predefined patch-level descriptors such as SIFT and HOG, the kernel descriptor (KD) method [1] offers a new way to `grow up' features from a match kernel defined over image patch pairs using kernel principal component analysis (KPCA). However, under this technical construction, all joint basis vectors are involved in the kernel descriptor computation, which is both expensive and not necessary. To address this problem, we present efficient kernel descriptor (EKD), which is built upon incomplete Cholesky decomposition. EKD automatically selects a small number of pivot features to achieve better computational efficiency. Perhaps due to parsimony, we find surprisingly that despite efficiency, the EKD approach achieved superior image/scene categorization performance than the original kernel descriptor approach.

Recently, sparse coding-based algorithms have achieved high performance on several popular scene classification benchmarks. Yet extensive efforts along this direction focus on strategies for coding and dictionary learning, few works have addressed the problem of optimal pooling regions selection. In this work, we show that the Viola-Jones algorithm, which is well-known in face detection, can be tailored to learning receptive fields for the sparse coding algorithms. Specifically, using the boosting approach to receptive field learning, image/scene categorization performance can be ubiquitously enhanced on several benchmarks (UIUC sport event, 15 natural scenes and the Caltech 101 dataset) to the state-of-the-art, using only low dimensional features and small codebook sizes. Furthermore, the “salient pooling regions” can be obtained explicitly.

BACKGROUND: Identification of transcription factor binding sites (also called 'motif discovery') in DNA sequences is a basic step in understanding genetic regulation. Although many successful programs have been developed, the problem is far from being solved on account of diversity in gene expression/regulation and the low specificity of binding sites. State-of-the-art algorithms have their own constraints (e.g., high time or space complexity for finding long motifs, low precision in identification of weak motifs, or the OOPS constraint: one occurrence of the motif instance per sequence) which limit their scope of application. RESULTS: In this paper, we present a novel and fast algorithm we call TFBSGroup. It is based on community detection from a graph and is used to discover long and weak (l,d) motifs under the ZOMOPS constraint (zero, one or multiple occurrence(s) of the motif instance(s) per sequence), where l is the length of a motif and d is the maximum number of mutations between a motif instance and the motif itself. Firstly, TFBSGroup transforms the (l, d) motif search in sequences to focus on the discovery of dense subgraphs within a graph. It identifies these subgraphs using a fast community detection method for obtaining coarse-grained candidate motifs. Next, it greedily refines these candidate motifs towards the true motif within their own communities. Empirical studies on synthetic (l, d) samples have shown that TFBSGroup is very efficient (e.g., it can find true (18, 6), (24, 8) motifs within 30 seconds). More importantly, the algorithm has succeeded in rapidly identifying motifs in a large data set of prokaryotic promoters generated from the Escherichia coli database RegulonDB. The algorithm has also accurately identified motifs in ChIP-seq data sets for 12 mouse transcription factors involved in ES cell pluripotency and self-renewal. CONCLUSIONS: Our novel heuristic algorithm, TFBSGroup, is able to quickly identify nearly exact matches for long and weak (l, d) motifs in DNA sequences under the ZOMOPS constraint. It is also capable of finding motifs in real applications. The source code for TFBSGroup can be obtained from http://bioinformatics.bioengr.uic.edu/TFBSGroup/.

In this paper, we study the image recovery problem where the observed image is simultaneously corrupted by blur and impulse noise. Our proposed patch-based model contains three terms: the sparse representation prior, the total variation regularization, and the data-fidelity term. We are interested in the two-phase approach. The first phase is to identify the possible impulse noise positions; the second phase is to recover the image via the patch-based model using noise position information. An alternating minimization method is then applied to solve the model. This approach works extremely well for image deblurring under salt-and-pepper noise. However, as the detection for random-valued noise is usually unreliable, extra work is then needed. Indeed, to get better recovery results for the latter case, we combine the two separate phases to simultaneously detect the random-valued noise positions and to recover the image. The numerical experiments clearly demonstrate the super performance of the proposed methods.

The restoration of images corrupted by blur and Poisson noise is a key issue in medical and biological image processing. While most existing methods are based on variational models, generally derived from a maximum a posteriori (MAP) formulation, recently sparse representations of images have shown to be efficient approaches for image recovery. Following this idea, we propose in this paper a model containing three terms: a patch-based sparse representation prior over a learned dictionary, the pixel-based total variation regularization term and a data-fidelity term capturing the statistics of Poisson noise. The resulting optimization problem can be solved by an alternating minimization technique combined with variable splitting. Extensive experimental results suggest that in terms of visual quality, peak signal-to-noise ratio value and the method noise, the proposed algorithm outperforms state-of-the-art methods.

In frequency domain blind source separation (FDBSS), separated frequency bin data in the same source must be grouped together before outputting the final result, which is the well-known permutation problem. Clustering techniques are broadly used in solving the permutation problem, however, some challenges still exist, for example, elongated datasets should be handled, and constraint from the background knowledge must be considered. Inspired by various successful applications of kernel and spectral clustering methods in machine learning and data mining community, we try to solve the permutation problem by these methods. In this paper, the weighted kernel k-means algorithm is modified according to the specific requirement of the permutation problem, and the spectral interpretation of the kernel approach is also investigated. In addition, we propose several kernel construction approaches to improving the permutation performance. Different experiments are carried out on a uniform platform, and show better performance of the proposed approach.

This paper addresses the problem of detecting salient areas within natural images. We shall mainly study the problem under unsupervised setting, i.e., saliency detection without learning from labeled images. A solution of multitask sparsity pursuit is proposed to integrate multiple types of features for detecting saliency collaboratively. Given an image described by multiple features, its saliency map is inferred by seeking the consistently sparse elements from the joint decompositions of multiple-feature matrices into pairs of low-rank and sparse matrices. The inference process is formulated as a constrained nuclear norm and as an l(2, 1)-norm minimization problem, which is convex and can be solved efficiently with an augmented Lagrange multiplier method. Compared with previous methods, which usually make use of multiple features by combining the saliency maps obtained from individual features, the proposed method seamlessly integrates multiple features to produce jointly the saliency map with a single inference step and thus produces more accurate and reliable results. In addition to the unsupervised setting, the proposed method can be also generalized to incorporate the top-down priors obtained from supervised environment. Extensive experiments well validate its superiority over other state-of-the-art methods.

Semi-supervised nonnegative matrix factorization (NMF)receives more and more attention in text mining field. The semi-supervised NMF methods can be divided into two types, one is based on the explicit category labels, the other is based on the pair wise constraints including must-link and cannot-link. As it is hard to obtain the category labels in some tasks, the latter one is more widely used in real applications. To date, all the constrained NMF methods treat the must-link and cannot-link constraints in a same way. However, these two kinds of constraints play different roles in NMF clustering. Thus a novel constrained NMF method is proposed in this paper. In the new method, must-link constraints are used to control the distance of the data in the compressed form, and cannot-ink constraints are used to control the encoding factor. Experimental results on real-world text data sets have shown the good performance of the proposed method.

This paper presents a convex vector-valued active contour model for texture segmentation. This model uses histograms of the semi-local region descriptor and image intensity for measuring the similarity of image regions. We use the Quadratic-Chi histogram distance to compare the dissimilarity of histograms. Quadratic-Chi histogram distance is a cross-bin distance that matches perceptual similarity better than the bin-to-bin distance (such as Kullback-Leibler divergence and Bhattacharyya distance). Then we use a primal-dual method to solve the minimization problem. Experimental results for real images show the effective of the proposed method.

Cluster analysis is a tool for data analysis. It is a method for finding clusters of a data set with most similarity in the same group and most dissimilarity between different groups. In general, there are two ways, mixture distributions and classifi

How best to represent text data is an important problem in text mining tasks including information retrieval, clustering, classification and etc.. In this paper, we proposed a compact document representation with term semantic units which are identified from the implicit and explicit semantic information. Among it, the implicit semantic information is extracted from syntactic content via statistical methods such as latent semantic indexing and information bottleneck. The explicit semantic information is mined from the external semantic resource (Wikipedia). The proposed compact representation model can map a document collection in a low-dimension space (term semantic units which are much less than the number of all unique terms). Experimental results on real data sets have shown that the compact representation efficiently improve the performance of text clustering.

Recent research has shown that keyword search is a friendly and potentially effective way to retrieve information of interest over relational databases. Existing work has generally focused on implementing keyword search in centralized databases. This paper addresses keyword search over distributed databases. We adopts distributed hash tables (DHTs) - a peer-to-peer inspired overlay network technology - as the infrastructure to implement keyword search over relational databases. For this end, we combine IR-based ranking techniques with a P2P-based indexing strategy, and propose an effective approach. Extensive experiments over real-world datasets show that our approach is effective and efficient.

In the fuzzy c-means (FCM) clustering algorithm, almost none of the data points have a membership value of 1. Moreover, noise and outliers may cause difficulties in obtaining appropriate clustering results from the FCM algorithm. The embedding of FCM into switching regressions, called the fuzzy c-regressions (FCRs), still has the same drawbacks as FCM. In this paper, we propose the alpha-cut implemented fuzzy clustering algorithms, referred to as FCMalpha, which allow the data points being able to completely belong to one cluster. The proposed FCMalpha algorithms can form a cluster core for each cluster, where data points inside a cluster core will have a membership value of 1 so that it can resolve the drawbacks of FCM. On the other hand, the fuzziness index m plays different roles for FCM and FCMalpha. We find that the clustering results obtained by FCMalpha are more robust to noise and outliers than FCM when a larger m is used. Moreover, the cluster cores generated by FCMalpha are workable for various data shape clusters, so that FCMalpha is very suitable for embedding into switching regressions. The embedding of FCMalpha into switching regressions is called FCRalpha. The proposed FCRalpha provides better results than FCR for environments with noise or outliers. Numerical examples show the robustness and the superiority of our proposed methods.

In this paper, we propose a generalized fuzzy clustering regularization (GFCR) model and then study its theoretical properties. GFCR unifies several fuzzy clustering algorithms, such as fuzzy c-means (FCM), maximum entropy clustering (MEC), fuzzy clustering based on Fermi-Dirac entropy, and fuzzy bidirectional associative clustering network, etc. The proposed GFCR becomes an alternative model of the generalized FCM (GFCM) that was recently proposed by Yu and Yang. To advance theoretical study, we have the following three considerations. 1) We give an optimality test to monitor if GFCR converges to a local minimum. 2) We relate the GFCR optimality tests to Occam's razor principle, and then analyze the model complexity for fuzzy clustering algorithms. 3) We offer a general theoretical method to evaluate the performance of fuzzy clustering algorithms. Finally, some numerical experiments are used to demonstrate the validity of our theoretical results and complexity analysis.

Partitional clustering is an important part of cluster analysis. Based on various theories, numerous clustering algorithms have been developed, and new clustering algorithms continue to appear in the literature. It is known that Occam's razor plays a pivotal role in data-based models, and partitional clustering is categorized as a data-based model. However, no relation had previously been discovered between Occam's razor and partitional clustering, as we discuss in this paper. The three main contributions of this paper can be summarized as follows: 1) According to a novel definition of the mean, a unifying generative framework for partitional clustering algorithms, called a general c-means clustering model (GCM), is presented and studied. 2) Based on the local optimality test of the GCM, the connection between Occam's razor and partitional clustering is established for the first time. As its application, a comprehensive review of the existing objective function-based clustering algorithms is presented based on GCM. 3) Under a common assumption about partitional clustering, a theoretical guide for devising and implementing clustering algorithm is discovered. These conclusions are verified by numerical experimental results.

In cluster analysis, the fuzzy c-means (FCM) clustering algorithm is the best known and most widely used method. It was proven to converge to either a local minimum or saddle points by Bezdek et al. Wei and Mendel produced efficient optimality tests for FCM fixed points. Recently, a weighting exponent selection for FCM was proposed by Yu et al. Inspired by these results, we unify several alternative FCM algorithms into one model, called the generalized fuzzy c-means (GFCM). This GFCM model presents a wide variation of FCM algorithms and can easily lead to new and interesting clustering algorithms. Moreover, we construct a general optimality test for GFCM fixed points. This is applied to theoretically choose the parameters in the GFCM model. The experimental results demonstrate the precision of the theoretical analysis.

In [1], Ozdemir and Akarun proposed an intercluster separation (ICS) fuzzy clustering algorithm. The ICS algorithm is useful in combined quantization and dithering. However, there are two errors in the update equations for the ICS algorithm. This correspondence first points out these errors and gives their corrections. Since the parameters m, c, and gamma are important factors in the performance of ICS, we also conduct a theoretical analysis of these ICS parameters. In order to analyze the parameters in ICS, we devise a theorem for the calculation of the Hessian matrix from the ICS objective function. We establish the fixed-point property of ICS based on the decomposition of the Hessian matrix and then analyze the effect of the parameters. Finally, we propose a numerical approach in choosing the appropriate parameters m and gamma for ICS. These experimental results give a better numerical perspective on the effect of parameters in ICS and have conclusions consistent with our theoretical analysis.

In the above-mentioned paper, Wei and Fahn proposed a neural architecture, the multisynapse neural network, to solve constrained optimization problems including high-order, logarithmic, and sinusoidal forms, etc. As one of its main applications, a fuzzy bidirectional associative clustering network (FBACN) was proposed for fuzzy-partition clustering according to the objective-functional method. The connection between the objective-functional-based fuzzy c-partition algorithms and FBACN is the Lagrange multiplier approach. Unfortunately, the Lagrange multiplier approach was incorrectly applied so that FBACN does not equivalently minimize its corresponding constrained objective-function. Additionally, Wei and Fahn adopted traditional definition of fuzzy c-partition, which is not satisfied by FBACN. Therefore, FBACN can not solve constrained optimization problems, either.

Intensity-based methods work well for multimodal image registration owing to their effectiveness and simplicity, but the computation for geometric transforms is a heavy load. To accelerate the transformation, in this paper, we present two shear-resize matrix factorizations for general 3D linear transformation, to factorize a transform matrix into three shears and a fixed resize, or four shears and a customizable resize. Shears can be implemented very fast by memory shift and a resize can be done by axis-aligned resampling. The factorizations can be applied to both rigid-body and affine transformations. The experiments on MRI and CT volumes show that our method is 10 times faster than the naive transformation. The method is quite promising for hardware and parallel implementation, and is also valid for monomodal image registration.

The fuzzy c-means (FCM) algorithm is one of the most frequently used clustering algorithms. The weighting exponent m is a parameter that greatly influences the performance of the FCM. But there has been no theoretical basis for selecting the proper weighting exponent in the literature. In this paper, we develop a new theoretical approach to selecting the weighting exponent in the FCM. Based on this approach, we reveal the relation between the stability of the fixed points of the FCM and the data set itself. This relation provides the theoretical basis for selecting the weighting exponent in the FCM. The numerical experiments verify the effectiveness of our theoretical conclusion.

Many partitional clustering algorithms originated from the definition of mean.We propose a new clustering model - general c-means clustering algorithm (GCM). Generally, when the data set is clustered into c (c > 1) subsets, each subset is often expected to have a different prototype (or cluster center) than others. Therefore, we propose the definition of undesirable solution of clustering algorithms. As the GCM has undesirable solution under a mild condition, undesirable solution of the GCM is not expected to be stable. According to these assumptions, we obtain the necessary conditions for the GCM as a good clustering model. Fortunately, such conditions have offered a theoretical basis for selection of the parameters in many clustering algorithms, which is an open problem for such algorithms, for example, we get the theoretical rule for selection of the weighting exponent in the FCM, and explain why the weighting exponent should be greater than 1, etc. Moreover, we discover the relation between the GCM model and Occam's razor, which offers the deep reason behind many famous partitional clustering algorithms. Based on these results, we can study many objective function based clustering algorithms.

It is always supposed that each cluster has almost equal number of points when carrying out the FCM. However, this assumption may not hold in practice. In this paper, we propose a novel fuzzy c-means algorithm based on the definition of generalized mean, weighting fuzzy c-means algorithms (WFCM). Noticing that the Gath-Geva fuzzy clustering algorithm considers the size of the clusters, we compare the performance between the WFCM and the Gath-Geva fuzzy clustering algorithms by numerical experiments. Moreover, we offer a theoretical threshold to choose an appropriate weighting exponent in the WFCM, which is also valid for the FCM, the numeric experiments verify such conclusion.

The fuzzy c-means algorithm (FCM) is proved to converge to either local minimum or saddle point by Bezdek et al.(1987). However, it is problematical to judge the local minimum of a solution of the FCM in an easy way. In this paper, the Hessian matrix of one reduced objective function of the FCM is obtained and analyzed. Based on this study, a new optimality test of fixed points of the FCM is given, and its efficacy is verified by the examples in the paper. Moreover, a new stopping criterion for the FCM is also proposed.