The advancement of autonomous driving technology has brought significant benefits to modern transportation systems. However, individual autonomous vehicles face challenges such as limited perception range and insufficient autonomous capabilities. Cooperative groups of autonomous vehicles, enabled by advanced communication technologies, can enhance traffic efficiency through information exchange. Existing research primarily focuses on centralized autonomous vehicle groups, where the leading node suffers from weak resilience and high computational load, making it difficult to maintain group collaboration over time. To address these issues, this article proposes a decentralized formation and self-adaptation method for autonomous vehicle social groups based on consensus resistance in closed scenes. First, we introduceconsensus resistanceas a metric to evaluate social group and member consistency, and develop a decentralized formation approach. Second, we present a self-adaption model for autonomous vehicle social groups, incorporating four evolutionary events: 1) expansion; 2) merging; 3) reduction; and 4) splitting, to ensure the stability of moving social groups. Simulation results demonstrate the proposed method effectively constructs social groups in both real-world and simulated environments, exhibiting robust consistency throughout the self-adaption process.

Current knowledge distillation methods typically require significant computational resources and time to train task-specific teacher candidates from scratch and identify the optimal teacher. Although self-distillation methods eliminate the dependency on the teacher by allowing the student model to learn independently, they face two challenges: the student learns correct and incorrect knowledge indiscriminately, and the student's learning scope is limited due to the lack of external teacher supervision. Spurred by these deficiencies, this work proposes a CLIP-enhanced Self-Distillation (CLIP-SD) method to overcome these problems, while almost not increasing training time. CLIP-SD comprises two main components: Prediction-oriented Self-Distillation (PSD) and Two-stage Task-guided CLIP Distillation (TTCD). PSD tackles the first challenge by assigning higher and lower weights to correct and incorrect prediction samples, respectively, during self-distillation. This component forces the student to focus on correct knowledge and minimize the impact of incorrect knowledge. Regarding the second challenge, the robust CLIP model is directly introduced into self-distillation. However, CLIP lacks task-specific knowledge and its output is overly smooth during the distillation process, prohibiting the student from learning more effectively. Therefore, TTCD refines CLIP's output through a two-stage process, endowing it with task-specific knowledge to enhance student learning. Experimental results indicate that CLIP-SD significantly improves distillation performance while maintaining training efficiency comparable to self-distillation. Specifically, on the CIFAR-100 dataset, the performance of CLIP-SD reaches 72.48% when trained with ResNet20 as the student model, which is an average improvement of 2.54% and 1.12% over the knowledge distillation and self-distillation methods. Regarding training time, CLIP-SD takes 3.91 hours, an average decrease of 2.73 hours compared to knowledge distillation and an average increase of 0.45 hours compared to self-distillation. Despite the slight increase in training time compared to self-distillation, the overhead is worthwhile and negligible considering its performance improvement.

Sequential recommendation systems have become essential for personalized services in e-commerce and content platforms. While recent research has extended these systems with multi-modal features, existing approaches face three major challenges. First, they inadequately model fine-grained temporal interval distributions, failing to discriminate between high-frequency short intervals and low-frequency long intervals. Second, uniform fusion in the time domain leads to semantic misalignment across modalities because it ignores their inherent differences in the frequency domain. Third, rigid fusion strategies without self-supervised constraints lead to limited representation quality and semantic drift from pretrained embeddings. To address these issues, we propose Adaptive Temporal Expert Routing with Hierarchical Wavelet Enhancement (ATHWE) framework. ATHWE employs exponential saturation time mapping to generate temporally adaptive embeddings. These embeddings guide a sparse mixture of experts to model multi-scale user behavior dynamics. A hierarchical wavelet decomposition with band-specific gating selectively fuses complementary frequency components across modalities. Furthermore, contrastive learning and cluster-preserving objectives preserve semantic information during multi-modal fusion. Extensive experiments on multiple datasets validate the effectiveness of our framework. Our code is available at https://github.com/lulusiyuyu/ATHWE .

Knowledge distillation transfers "dark knowledge" from a large teacher model to a smaller student model, yielding a highly efficient network. To improve network's generalization ability, existing works use a larger temperature coefficient for knowledge distillation. Nevertheless, these methods may lower the target category's confidence and lead to ambiguous recognition of similar samples. To mitigate this issue, some studies introduce intra-batch distillation to reduce prediction discrepancy. However, these methods overlook the inconsistency between background information and the target category, which may increase prediction bias due to noise disturbance. Additionally, label imbalance from random sampling and batch size can undermine network generalization reliability. To tackle these challenges, we propose a simple yet effective Intra-class Knowledge Distillation (IKD) method that facilitates knowledge sharing within the same class to ensure consistent predictions. First, we initialize the matrix and the vector to store logits and class counts provided by the teacher, respectively. Then, in the first epoch, we calculate the sum of logits and sample counts per class and perform KD to prevent knowledge omission. Finally, in subsequent training, we update the matrix to obtain the average logits and compute the KL divergence between the student's output and the updated matrix according to the label index. This process ensures intra-class consistency and improves the student's performance. Furthermore, this method theoretically reduces prediction bias by ensuring intra-class consistency. Extensive experiments on the CIFAR-100, ImageNet-1K, and Tiny-ImageNet datasets validate the superiority of IKD.

Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preserving their generalization capabilities remains challenging. Although prompt learning methods have shown promise, they suffer from two fundamental bottlenecks that limit generalization: (a) modality isolation, and (b) hierarchical semantic decay. To address these limitations, we propose HiCroPL, a Hierarchical Cross-modal Prompt Learning framework that establishes bidirectional knowledge flow between text and vision modalities, enabling them to refine their semantics mutually. HiCroPL routes knowledge flows by leveraging the complementary strengths of text and vision. In early layers, text prompts inject relatively clear semantics into visual prompts through a hierarchical knowledge mapper, enhancing the representation of low-level visual semantics. In later layers, visual prompts encoding specific task-relevant objects flow back to refine text prompts, enabling deeper alignment. Crucially, our hierarchical knowledge mapper allows representations at multi-scales to be fused, ensuring that deeper representations retain transferable shallow semantics thereby enhancing generalization. We further introduce a lightweight layer-specific knowledge proxy to enable efficient cross-modal interactions. Extensive evaluations across four tasks demonstrate HiCroPL's superior performance, achieving state-of-the-art results on 11 benchmarks with significant improvements. Code is available at: https://github.com/zzeoZheng/HiCroPL.

Offset-based representation has emerged as a promising approach for modeling semantic relations between pixels and object motion, demonstrating efficacy across various computer vision tasks. In this paper, we introduce a novel one-stage multi-tasking network tailored to extend the offset-based approach to MOTS. Our proposed framework, named OffsetNet, is designed to concurrently address amodal bounding box detection, instance segmentation, and tracking. It achieves this by formulating these three tasks within a unified pixel-offset-based representation, thereby achieving excellent efficiency and encouraging mutual collaborations. OffsetNet achieves several remarkable properties: first, the encoder is empowered by a novel Memory Enhanced Linear Self-Attention (MELSA) block to efficiently aggregate spatial-temporal features; second, all tasks are decoupled fairly using three lightweight decoders that operate in a one-shot manner; third, a novel cross-frame offsets prediction module is proposed to enhance the robustness of tracking against occlusions. With these merits, OffsetNet achieves 76.83% HOTA on KITTI MOTS benchmark, which is the best result without relying on 3D detection. Furthermore, OffsetNet achieves 74.83% HOTA at 50 FPS on the KITTI MOT benchmark, which is nearly 3.3 times faster than CenterTrack with better performance. We hope our approach will serve as a solid baseline and encourage future research in this field.

Person re-identification (ReID) is vital for surveillance, tracking, and criminal investigations, yet occlusions often lead to partial information loss and noisy features that significantly degrade ReID performance. Recent CLIP-based occluded person ReID methods have demonstrated promising performance by leveraging cross-modal alignment, but still face two limitations: first, generic text prompts fail to capture the fine-grained semantics of specific samples; second, there is a lack of effective enhancement mechanisms for hard local features in occlusion scenarios. To overcome these limitations, we propose a Semantically Guided and Focused Network (SGFNet), which comprises three synergistic modules. First, to tackle the absence of fine-grained textual descriptions, we design a Segmentation and Text Generation (STG) module that segments pedestrian regions and generates sample-specific text features, providing detailed text descriptions and spatial information for local pedestrian regions. In addition, in order to accurately extract fine-grained features, we propose a Dual-guided Feature Refinement (DGFR) module. This module leverages a spatial attention mechanism guided by dual-semantic information to enhance discriminative fine-grained features while effectively suppressing interference from irrelevant regions. Finally, building upon the DGFR module, we further propose a Hardness-aware Semantic Focus (HASF) module. This module leverages segmentation cues to assess the difficulty of distinguishing local regions and employs a carefully designed Semantic-driven Focal Triplet loss to specifically enhance hard local feature learning, thereby improving the model’s robustness in feature extraction under occlusion scenarios. Extensive experiments demonstrate the superiority of SGFNet, achieving state-of-the-art performance on three occluded person ReID datasets while maintaining competitive results on three holistic person ReID datasets.

Aviation accidents are frequently related to pilots’ operations, especially during a landing phase. Therefore, accurately evaluating a pilot’s performance during this phase is crucial for minimizing landing risks. Traditional assessment methods, however, primarily focus on discrete monitoring points, failing to capture the continuous and dynamic nature of a pilot’s performance throughout the entire landing phase. To address this issue, we propose a Flight Process Importance (FPI) assessment framework that precisely determines accurate landing timing and captures the diverse operational characteristics of pilots. It consists of two components: Time-varying Importance Coefficient (TIC) and Pilot Characteristics Matrix (PCM). TIC develops a Spatio-Temporally Consistent Attention Network (STCAN) to classify Quick Access Recorder (QAR) data for anomalous event detection. It then determines the importance of different periods during the landing process by analyzing the STCAN model’s response to the data in an interpretable manner. PCM generates a parameter matrix for each flight by deriving the ideal intervals of various parameters through the interquartile range. This matrix is used to identify the duration and intensity of anomalies in operations across different pilots. By integrating TIC and PCM, our framework computes an evaluation matrix for each flight, quantifying the operational risk factors associated with pilots. Experimental results indicate that STCAN significantly surpasses other algorithms on QAR data. FPI provides a more precise and comprehensive assessment of a pilot’s performance. In particular, our findings highlight that the 10 seconds before landing to the touchdown are the most critical period of airplane landing.

Knowledge distillation (KD), as an effective compression technology, is used to reduce the resource consumption of graph neural networks (GNNs) and facilitate their deployment on resource-constrained devices. Numerous studies exist on GNN distillation, and however, the impacts of knowledge complexity and differences in learning behavior between teachers and students on distillation efficiency remain underexplored. We propose a KD method for fine-grained learning behavior (FLB), comprising two main components: feature knowledge decoupling (FKD) and teacher learning behavior guidance (TLBG). Specifically, FKD decouples the intermediate-layer features of the student network into two types: teacher-related features (TRFs) and downstream features (DFs), enhancing knowledge comprehension and learning efficiency by guiding the student to simultaneously focus on these features. TLBG maps the teacher model's learning behaviors to provide reliable guidance for correcting deviations in student learning. Extensive experiments across eight datasets and 12 baseline frameworks demonstrate that FLB significantly enhances the performance and robustness of student GNNs within the original framework.

Existing studies on knowledge distillation typically focus on teacher-centered methods, in which the teacher network is trained according to its own standards before transferring the learned knowledge to a student one. However, due to differences in network structure between the teacher and the student, the knowledge learned by the former may not be desired by the latter. Inspired by human educational wisdom, this paper proposes a Student-Centered Distillation (SCD) method that enables the teacher network to adjust its knowledge transfer according to the student network's needs. We implemented SCD based on various human educational wisdom, e.g., the teacher network identified and learned the knowledge desired by the student network on the validation set, and then transferred it to the latter through the training set. To address the problems of current deficiency knowledge, hard sample learning and knowledge forgetting faced by a student network in the learning process, we introduce and improve Proportional-Integral-Derivative (PID) algorithms from automation fields to make them effective in identifying the current knowledge required by the student network. Furthermore, we propose a curriculum learning-based fuzzy strategy and apply it to the proposed PID control algorithm, such that the student network in SCD can actively pay attention to the learning of challenging samples after with certain knowledge. The overall performance of SCD is verified in multiple tasks by comparing it with state-of-the-art ones. Experimental results show that our student-centered distillation method outperforms existing teacher-centered ones.

The recommendation of long-tail items has been a persistent issue in recommender system research. The primary reason for this problem is that the model cannot learn better item features due to the lack of interactive record data of tail items, which leads to a decline in the model's recommendation performance. Existing methods transfer the features of the head items to the tail items, thereby ignoring their differences and failing to produce a satisfactory recommendation effect. To address the issue, we propose a novel recommendation model called MetaGA based on metalearning. The MetaGA model obtains initial parameters from head items through metalearning and fine-tunes model parameters during the learning process of tail item features. Additionally, it employs a graph convolutional network and attention mechanism to enhance tail data and reduce the difference between head and tail data. Through the above two steps, the model utilizes the abundant data of the head items to address the problem of sparse data of the tail items, resulting in improved recommendation performance. We conducted extensive experiments on three real-world datasets, and the results demonstrate that our proposed MetaGA model significantly outperforms other state-of-the-art baselines for tail item recommendation.

Knowledge distillation (KD) is a technique that transfers “dark knowledge” from a deep teacher network (teacher) to a shallow student network (student). Despite significant advances in KD, existing work has not adequately mined two crucial types of knowledge: 1) the knowledge of head categories, which represents the relationship between the target category and its similar categories. Our findings reveal that this highly similar (complex) knowledge is essential for improving student’s performance; and 2) the effectively utilized knowledge of tail categories. Existing studies often treat the non-target categories collectively without sufficiently considering the effectiveness of knowledge from tail categories. To tackle these challenges, we reformulate classical KD (ReKD) into two components: Top-KInter-class Similar Distillation (TISD) and Non-Top-KInter-class Discriminability (NTID). Firstly, TISD captures and imparts the knowledge of head categories to the student. Our experimental results have verified that TISD is particularly effective in transferring the knowledge of head categories, even in fine-grained dataset classification. Secondly, we theoretically show that the weighting coefficient of NTID increases with the probability of Top-K, leading to stronger suppression of knowledge transfer for tail categories. This observation explains why difficult samples are more informative than simple ones. To better utilize both types of knowledge, we optimize both TISD and NTID using different weighting coefficients, thereby enhancing the student’s ability to learn this valuable knowledge from both head and tail categories. Furthermore, our extensive experimental results demonstrate that ReKD achieves state-of-the-art performance on various image classification datasets, including CIFAR-100, Tiny-ImageNet, and ImageNet-1K, as well as object detection and instance segmentation using the MS-COCO dataset.

Knowledge distillation, a widely adopted model compression technique, distils knowledge from a large teacher model to a smaller student model, with the goal of reducing the computational resources required for the student model. However, most existing distillation approaches focus on the types of knowledge and how to distil them, which neglect the student model's neuronal responses to the knowledge. In this article, we demonstrate that the kullback-leibler loss inhibits the neuronal responses in the opposite gradient direction, which injures the student model's potential during distilling. To address this problem, we introduce a principled dual-stage distillation scheme to rejuvenate all inhibited neurons at the neuronal level. In the first stage, we detect all the neurons in the student model during the standard distillation period and divide them into two parts according to their responses. In the second stage, we propose three strategies to resuscitate the neurons differently, which allows us to exploit the full potential of the student model. Through the experiments in various aspects of knowledge distillation, it is verified that the proposed approach outperforms the current state-of-the-art approaches. Our work provides a neuronal perspective for studying the response of the student model to the knowledge from the teacher model.

Convolutional neural networks (CNNs) have demonstrated excellent capability in various visual recognition tasks but impose an excessive computational burden. The latter problem is commonly solved by utilizing lightweight sparse networks. However, such networks have a limited receptive field in a few layers, and the majority of these networks face a severe information barrage due to their sparse structures. Spurred by these deficiencies, this work proposes a Squeeze Convolution block with Information Flow Enhancement (SCIFE), comprising a Divide-and-Squeeze Convolution and an Information Flow Enhancement scheme. The former module constructs a multi-layer structure through multiple squeeze operations to increase the receptive field and reduce computation. The latter replaces the affine transformation with the point convolution and dynamically adjusts the activation function’s threshold, enhancing information flow in both channels and layers. Moreover, we reveal that the original affine transformation may harm the network’s generalization capability. To overcome this issue, we utilize a point convolution with a zero initial mean. SCIFE can serve as a plug-and-play replacement for vanilla convolution blocks in mainstream CNNs, while extensive experimental results demonstrate that CNNs equipped with SCIFE compress benchmark structures without sacrificing performance, outperforming their competitors.

Knowledge distillation is a deep learning method that mimics the way that humans teach, i.e., a teacher network is used to guide the training of a student one. Knowledge distillation can generate an efficient student network to facilitate deployment in resource-constrained edge computing devices. Existing studies have typically mined knowledge from a teacher network and transferred it to a student one. The latter can only passively receive knowledge but cannot understand how the former acquires the knowledge, thus limiting the latter’s performance improvement. Inspired by the old Chinese saying “Give a man a fish and you feed him for a day; teach a man how to fish and you feed him for a lifetime,” this work proposes a Skill-transferring Knowledge Distillation (SKD) method to boost a student network’s ability to create new valuable knowledge. SKD consists of two main meta-learning networks: Teacher Behavior Teaching and Teacher Experience Teaching. The former captures the process of a teacher network’s learning behavior in the hidden layers and can predict the teacher network’s subsequent behavior based on previous ones. The latter models the optimal empirical knowledge of a teacher network’s output layer at each learning stage. With their help, a teacher network can provide its actions to a student one in the subsequent behavior and its optimal empirical knowledge in the current stage. SKD’s performance is verified through its application to multiple object recognition tasks and comparison with the state of the art.

Review-based recommender systems (RRS) have received an increasing interest since reviews greatly enhance recommendation quality and interpretability. However, existing RRS suffer from high computational complexity, biased recommendation and poor generalization. The three problems make them inadequate to handle real recommendation scenarios. Previous studies address each issue separately, while none of them consider solving three problems together under a unified framework. This paper presents LUME (a Lightweight Unbiased Multi-teacher Ensemble) for RRS. LUME is a novel framework that addresses the three problems simultaneously. LUME uses multi-teacher ensemble and debiased knowledge distillation to aggregate knowledge from multiple pretrained RRS, and generates a small, unbiased student recommender which generalizes better. Extensive experiments on various real-world benchmarks demonstrate that LUME successfully tackles the three problems and has superior performance than state-of-the-art RRS and knowledge distillation based RS.

Graph convolutional network (GCN)-based recommendation has recently attracted significant attention in the recommender system community. Although current studies propose various GCNs to improve recommendation performance, existing methods suffer from two main limitations. First, user–item interaction data is generally sparse in practice, highlighting these methods' ineffectiveness in learning user and item feature representations. Second, they usually perform a dot-product operation to model and calculate user preferences on items, leading to inaccurate user preference learning. To address these limitations, this study adopts a design idea that sharply differs from existing works. Specifically, we introduce the knowledge distillation concept into GCN-based recommendation and propose a two-phase knowledge distillation model (TKDM) improving recommendation performance. In Phase I, a self-distillation method on a graph auto-encoder learns the user and item feature representations. This auto-encoder employs a simple two-layer GCN as an encoder and a fully connected layer as a decoder. On this basis, in Phase II, a mutual-distillation method on a fully connected layer is introduced to learn user preferences on items with triple-based Bayesian personalized ranking. Extensive experiments on three real-world data sets demonstrate that TKDM outperforms classic and state-of-the-art methods related to GCN-based recommendation problems.

Sentence representation approaches have been widely used and proven to be effective in many text modeling tasks and downstream applications. Many recent proposals are available on learning sentence representations based on deep neural frameworks. However, these methods are pre-trained in open domains and depend on the availability of large-scale data for model fitting. As a result, they may fail in some special scenarios, where data are sparse and embedding interpretations are required, such as legal, medical, or technical fields. In this paper, we present an unsupervised learning method to exploit representations of sentences for some closed domains via topic modeling. We reformulate the inference process of the sentences with the corresponding contextual sentences and the associated words, and propose an effective context-enhanced process called the bi-Directional Context-enhanced Sentence Representation Learning (bi-DCSR). This method takes advantage of the semantic distributions of the nearby contextual sentences and the associated words to form a context-enhanced sentence representation. To support the bi-DCSR, we develop a novel Bayesian topic model to embed sentences and words into the same latent interpretable topic space called the Hybrid Priors Topic Model (HPTM). Based on the defined topic space by the HPTM, the bi-DCSR method learns the embedding of a sentence by the two-directional contextual sentences and the words in it, which allows us to efficiently learn high-quality sentence representations in such closed domains. In addition to an open-domain dataset from Wikipedia, our method is validated using three closed-domain datasets from legal cases, electronic medical records, and technical reports. Our experiments indicate that the HPTM significantly outperforms on language modeling and topic coherence, compared with the existing topic models. Meanwhile, the bi-DCSR method does not only outperform the state-of-the-art unsupervised learning methods on closed domain sentence classification tasks, but also yields competitive performance compared to these established approaches on the open domain. Additionally, the visualizations of the semantics of sentences and words demonstrate the interpretable capacity of our model.

Forming a stable autonomous vehicle group is extremely challenging in a highway scene that has several entrances and exits. Existing studies focus on centralized autonomous vehicle groups with leading nodes. Such groups suffer from unbalanced computing tasks, asymmetric information, and weak stability. This article introduces a side chain consensus-based decentralized autonomous vehicle group formation method in a highway scene. First, we side chain consensus to describe states of autonomous vehicles. Then, we give decentralized autonomous vehicle group formation and maintenance methods based on side chain consensus. Finally, we conduct simulations to evaluate the quality of side chain consensus and stability of vehicle groups, which shows that our method has better properties in the balance of computing tasks, information symmetry, and stability than existing methods.

Intelligent video surveillance is an important computer vision application in natural environments. Since detected objects under surveillance are usually low-resolution and noisy, their accurate recognition represents a huge challenge. Knowledge distillation is an effective method to deal with it, but existing related work usually focuses on reducing the channel count of a student network, not feature map size. As a result, they cannot transfer "privilege information" hidden in feature maps of a wide and deep teacher network into a thin and shallow student one, leading to the latter's poor performance. To address this issue, we propose a Feature Map Distillation (FMD) framework under which the feature map size of teacher and student networks is different. FMD consists of two main components: Feature Decoder Distillation (FDD) and Feature Map Consistency-enforcement (FMC). FDD reconstructs the shallow texture features of a thin student network to approximate the corresponding samples in a teacher network, which allows the high-resolution ones to directly guide the learning of the shallow features of the student network. FMC makes the size and direction of each deep feature map consistent between student and teacher networks, which constrains each pair of feature maps to produce the same feature distribution. FDD and FMC allow a thin student network to learn rich "privilege information" in feature maps of a wide teacher network. The overall performance of FMD is verified in multiple recognition tasks by comparing it with state-of-the-art knowledge distillation methods on low-resolution and noisy objects.

Recently, an attention mechanism has been used to help recommender systems grasp user interests more accurately. It focuses on their pivotal interests from a psychology perspective. However, most current studies based on it only focus on part of user interests; they have not mined user preferences thoroughly. To address the above problem, we propose a novel recommendation model: comparative convolutional dynamic multi-attention (CCDMA). This model provides a more accurate approach to represent user and item features and uses multi-attention-based convolutional neural networks to extract user and item latent feature vectors dynamically. The multi-attention mechanism considers both self-attention and cross-attention. Self-attention refers to the internal attention within users and items; cross-attention is the mutual attention between users and items. Moreover, we propose an optimized comparative learning framework that can mine the ternary relationships between one user and a pair of items, focusing on their relative relationship and the internal link between a pair of items. Extensive experiments on several real-world data sets show that the CCDMA model significantly outperforms state-of-the-art baselines in terms of different evaluation metrics.

Group recommendation has recently drawn a lot of attention to the recommender system community. Currently, several deep learning-based approaches are leveraged to learn preferences of groups for items and predict next items in which groups may be interested. Yet, their recommendation performance is still unsatisfactory due to sparse group–item interactions. To address this challenge, this study presents a novel model, called group recommendation model with two-stage deep learning (GRMTDL), which encompasses two sequential stages: 1) group representation learning (GRL) and 2) group preference learning (GPL). In GRL, we first construct an undirected tripartite graph over group–user–item interactions, and then employ it to accurately learn group semantic features through a spatial-based variational graph autoencoder network. While in GPL, we first introduce a dual PL-network that contains two structure-sharing subnetworks: 1) group PL-network employed for GPL and 2) user PL-network utilized for user preference learning. Then, we design a novel layered transfer learning (LTL) method to learn group preferences by alternately optimizing these two subnetworks. In particular, it can effectively absorb knowledge of user preferences into the process of GPL. Furthermore, extensive experiments on four real-world datasets demonstrate that the proposed GRMTDL model outperforms the state-of-the-art baselines for group recommendation.

Online text streams such as Twitter are the major information source for users when they are looking for ongoing events. Realtime event summarization aims to generate and update coherent and concise summaries to describe the state of a given event. Due to the enormous volume of continuously coming texts, realtime event summarization has become the de facto tool to facilitate information acquisition. However, there exists a challenging yet unexplored issue in current text summarization techniques: how to preserve the integrity, i.e., the accuracy and consistency of summaries during the update process. The issue is critical since online text stream is dynamic and conflicting information could spread during the event period. For example, conflicting numbers of death and injuries might be reported after an earthquake. Such misleading information should not appear in the earthquake summary at any timestamp. In this article, we present a novel realtime event summarization framework called IAEA (i.e., Integrity-Aware Extractive-Abstractive realtime event summarization). Our key idea is to integrate an inconsistency detection module into a unified extractive–abstractive framework. In each update, important new tweets are first extracted in an extractive module, and the extraction is refined by explicitly detecting inconsistency between new tweets and previous summaries. The extractive module is able to capture the sentence-level attention which is later used by an abstractive module to obtain the word-level attention. Finally, the word-level attention is leveraged to rephrase words. We conduct comprehensive experiments on real-world datasets. To reduce efforts required for building sufficient training data, we also provide automatic labeling steps of which the effectiveness has been empirically verified. Through experiments, we demonstrate that IAEA can generate better summaries with consistent information than state-of-the-art approaches.

Maintaining network connectivity is an important challenge for vehicular ad hoc network (VANET) in an urban scene, which has more complex road conditions than highways and suburban areas. Most existing studies analyze end-to-end connectivity probability under a certain node distribution model, and reveal the relationship among network connectivity, node density, and a communication range. Because of various influencing factors and changing communication states, most of their results are not applicable to VANET in an urban scene. In this article, we propose a connectivity prediction-based dynamic clustering (DC) model for VANET in an urban scene. First, we introduce a connectivity prediction method (CP) according to the features of a vehicle node and relative features among vehicle nodes. Then, we formulate a DC model based on connectivity among vehicle nodes and vehicle node density. Finally, we present a DC model-based routing method to realize stable communications among vehicle nodes. The experimental results show that the proposed CP can achieve a lower error rate than the geographic routing based on predictive locations and multilayer perceptron. The proposed routing method can achieve lower end-to-end latency and higher delivery rate than the greedy perimeter stateless routing and modified distributed and mobility-adaptive clustering-based methods.

Location-based recommendation has recently received a lot of attention in the communities of information service and mobile application. Its task is to provide personalized recommendations of points of interest (POIs) to users at a certain time and location. However, existing location-based recommendation models have at least two main drawbacks: first they cannot adequately capture semantic features of POIs and users, which may lead to unsatisfactory recommendations and second they cannot effectively address the cold-start problem. To address the above drawbacks, in this article, we first propose a novel deep representation learning-based model (DRLM) for improving the recommendation accuracy. In DRLM, we mainly focus on learning to accurately represent semantic features of POIs and users. Specifically, four co-occurrence matrices are constructed to produce four different original features for each POI, and a principal component analysis (PCA) algorithm is utilized to generate a semantic feature of each POI from its four original features. On the other hand, a three-modal simple recurrent unit (TMSRU) network is given to constructed semantic features of users using semantic features of POIs, times, and locations. We further propose minimum description length (MDL)-based and skyline-based strategies to address the cold-start issues for new users and new POIs, respectively. Through experiments on two real-world data sets, we show that compared with the state-of-the-art approaches, the proposed model DRLM can achieve the superior performance in terms of high recommendation accuracy and effectiveness in handling the cold-start problem.

In recent years, group recommendation has become a research hotspot and focus in online social network community. Currently, several deep-learning-based approaches are leveraged to learn preferences of groups for items and predict the next items in which groups may be interested. Yet, their recommendation performance is still unsatisfactory due to the sparse group-item interactions. In order to address this problem, in this article, we introduce an effective model, namely Social Group Recommendation model with TrAdaBoost (SGRTAB), to raise the performance of group recommendation in online social networks. The SGRTAB model includes two stages: data preprocessing (DP) and model optimization (MO). In DP, SGRTAB produces inputs for MO and implements three related tasks: extracting individual features, handling group data via GloVe, and utilizing user contribute ratings to their own groups, whereas in MO, SGRTAB implements group preference learning with the assistance of user preference learning based on the TrAdaBoost algorithm. Specifically, SGRTAB can effectively absorb the knowledge of user preferences into the process of group preference learning through the idea of transferring-ensemble learning. Moreover, extensive experiments on four real-world data sets indicate that the proposed SGRTAB model significantly outperforms the state-of-the-art baselines for social group recommendation.

Group recommendation research has recently received much attention in a recommender system community. Currently, several deep-learning-based methods are used in group recommendation to learn preferences of groups on items and predict the next ones in which groups may be interested. However, their recommendation effectiveness is disappointing. To address this challenge, this article proposes a novel model called a multiattention-based group recommendation model (MAGRM). It well utilizes multiattention-based deep neural network structures to achieve accurate group recommendation. We train its two closely related modules: vector representation for group features and preference learning for groups on items. The former is proposed to learn to accurately represent each group's deep semantic features. It integrates four aspects of subfeatures: group co-occurrence, group description, and external and internal social features. In particular, we employ multiattention networks to learn to capture internal social features for groups. The latter employs a neural attention mechanism to depict preference interactions between each group and its members and then combines group and item features to accurately learn group preferences on items. Through extensive experiments on two real-world databases, we show that MAGRM remarkably outperforms the state-of-the-art methods in solving a group recommendation problem.

Using large-scale GPS trajectory data to improve taxi services has recently attracted much attention in Internet of Things and smart city communities. In this paper, we use a large-scale GPS trajectory dataset generated by over 12 000 taxis in a period of three months in Shanghai, China, and present an efficient passenger-hunting recommendation framework with the multitask deep learning paradigm. This framework contains two modules: 1) offline training of passenger-hunting recommendation model (OT-PHRM) and 2) online application of passenger-hunting recommendation model (OA-PHRM). The module OT-PHRM mainly includes two deep convolutional neural networks (DCNNs) and uses the multitask learning strategy. The first DCNN realizes the region prediction for picking up passengers, while the second DCNN uses the weight-sharing structure to predict the levels of road congestion and earnings of carrying passengers. In particular, for the input of two DCNNs, we not only consider contextual features of taxi driving, region features and valuable statistical features, but also combine individual features into meaningful ones. In the module OA-PHRM, we propose DL-PHRec, which calculates three prediction values using two trained DCNNs in OT-PHRM in real time, and then recommends a personal ranking-list of regions to each taxi driver according to their scores. The experimental results show the feasibility and effectiveness of our recommendation framework.

The recommender system has recently drawn a lot of attention to the communities of information services and mobile applications. Many deep learning-based recommendation models have been proposed to learn the feature representations from items. However, in Internet of Things (IoT), items' description information are typically heterogeneous and multimodal, posing a challenge to items' representation learning of recommendation models. To address this challenge and to improve the recommendation effectiveness in IoT, a novel multimodal representation learning-based model (MRLM) has been proposed. In MRLM, two closely related modules were trained simultaneously; they are global feature representation learning and multimodal feature representation learning. The former was designed to learn to accurately represent the global features of items and users through simultaneous training on three tasks: 1) triplet metric learning; 2) softmax classification; and 3) microscopic verification. The latter was proposed to refine items' global features and to generate the final multimodal features by using items' multimodal description information. After MRLM converged, items' multimodal features and users' global features could be used to calculate users' preferences on items via cosine similarity. Through extensive experiments on two real-world datasets, MRLM remarkably improved the recommendation effectiveness in IoT.

It is an important challenge to detect an overlapping community and its evolving tendency in a complex network. To our best knowledge, there is no such an overlapping community detection method that exhibits high normalized mutual information (NMI) and F-score, and can also predict an overlapping community's future considering node evolution, activeness, and multiscaling. This paper presents a novel method based on node vitality, an extension of node fitness for modeling network evolution constrained by multiscaling and preferential attachment. First, according to a node's dynamics such as link creation and destruction, we find node vitality by comparing consecutive network snapshots. Then, we combine it with the fitness function to obtain a new objective function. Next, by optimizing the objective function, we expand maximal cliques, reassign overlapping nodes, and find the overlapping community that matches not only the current network but also the future version of the network. Through experiments, we show that its NMI and Fscore exceed those of the state-of-the-art methods under diverse conditions of overlaps and connection densities. We also validate the effectiveness of node vitality for modeling a node's evolution. Finally, we show how to detect an overlapping community in a real-world evolving network.

Exponential growth of information generated by social networks requires efficient and scalable recommendation techniques to produce useful results. Traditional methods have become unqualified because they consider only ratings instead of rankings in an item list, and they ignore social contextual information, which is valuable for predicting users’ preference. It is significant and challenging to fuse social contextual information into learning to recommendation methods. In this study, the authors first extend user latent features by exploiting users’ social relationship such as friendship or trust relations, and extend item latent features with concurrent items. Then they integrate both users’ and items’ social contextual information into a pairwise learning to recommendation model (named as UIContextRank) to enhance ranking accuracy and recommendation quality. Furthermore, they extend UIContextRank in a distributed environment to improve efficiency and scalability. The authors conduct experiments on both bidirectional and unidirectional social network datasets. The results show that their method significantly outperforms other approaches.

ABSTRACT Nowadays, social network site (SNS) has been a popular platform for information sharing and dissemination. However, because of unknown information sources or unfamiliar recommenders, users of SNS may receive thousands of recommending information, which contain potential risks to receivers. To meet the challenge of confirming reliabilities of recommendations, a novel method of recommended trust computation is proposed in this paper. Firstly, according to the elements of users' relationships and community characteristics in SNS, concepts of belief and reputation are defined to express subjective trustable relationship among individuals and objective trust view. Then, recommended trust computation is presented on the basis of aforementioned two concepts. The recommended trust computation is divided into two aspects, that is, recommended trust computation with different route composition and recommendation optional confidence. Further, a SNS recommended trust computation framework is proposed. Finally, examinations are given to further explain the efficiency and feasibility of our mechanism. Copyright © 2014 John Wiley & Sons, Ltd.

A variety of news recommender systems based on different strategies have been proposed to provide news personalization services for online news readers. However, little research work has been reported on utilizing the implicit "social" factors (i.e., the potential influential experts in news reading community) among news readers to facilitate news personalization. In this paper, we investigate the feasibility of integrating content-based methods, collaborative filtering and information diffusion models by employing probabilistic matrix factorization techniques. We propose PRemiSE, a novel Personalized news Recommendation framework via implicit Social Experts, in which the opinions of potential influencers on virtual social networks extracted from implicit feedbacks are treated as auxiliary resources for recommendation. Empirical results demonstrate the efficacy and effectiveness of our method, particularly, on handling the so-called cold-start problem.

The flooding of low-quality user generated contents (UGC) in online social network (OSN) has been a threat to web knowledge management systems. Recently several domain-specific systems have been developed addressing this problem, for example, predict correct answer in QA community; recognise reliable comment in products review forums etc. Major drawback of most research efforts is the lack of a general framework applicable to all OSNs. In this study, the authors start by analysing the effects of distinguishing features on UGC quality in different types of OSNs. Extensive statistical analysis leads to the discovery of existence of diverse patterns of human information sharing activity in dissimilar OSNs. This discovery is employed as prior knowledge in the classification framework, which decompose the original highly imbalanced problem into several balanced sub-problems. Ensemble classifiers are adopted in samples from clusters generated by incompact features. Experiments show the proposed framework is both effective and efficient for several OSNs.Contributions of this study are two-fold: (i) model posting activity in different types of OSNs; (ii) propose novel classification framework to identify UGC quality.

It is an important issue to get support from experts in our daily life. Expert finding is challenging. In previous commercial and academic systems, the users may not get what they expect. In this contribution, we address the problem of finding experts in communities. A novel model REC is presented to solve the expert finding problem in dynamic environment. The model ranks experts by textural and social information. Starting with the most familiar communities, the expert seeker may find appropriate experts, by considering both their local rankings in each community and the difficulty to get their help. Experiments are done on real data sets, including DBLP data set and W3C corpora. Compared with other existing methods, REC achieves promising results. It demonstrates the model's competencies in various search applications.