Large Language Models (LLMs) offer groundbreaking advancements in recommender systems through superior text analysis and decision-making support. However, integrating LLMs into recommender systems still suffers from the problems of identifier uninterpretability and lack of transparency. To address these issues and fully leverage the capabilities of LLMs, we propose a chain of thought (CoT) based recommendation framework called CoT4Rec which employs LLMs as data enhancers for user preference analysis. Initially, we design a CoT reasoning strategy that can derive more behaviorally-aligned user preference features by clustering users’ historical interactions. Subsequently, we propose a two-stage recommendation model that not only makes full use of the world knowledge embedded in LLMs but also generates a logically transparent reasoning path. By integrating a user preference analyzer early in the recommendation pipeline, the model deeply analyzes users' historical interactions, helping to enhance the personalization and transparency of the recommender system. CoT4Rec demonstrates superior performance over existing state-of-the-art models in recommendation tasks across four public datasets, achieving improvements ranging from 2.2% to 12.2%.

Trajectory inference is a crucial task in single-cell RNA-sequencing downstream analysis, which can reveal the dynamic processes of biological development, including cell differentiation. Dimensionality reduction is an important step in the trajectory inference process. However, most existing trajectory methods rely on cell features derived from traditional dimensionality reduction methods, such as principal component analysis and uniform manifold approximation and projection. These methods are not specifically designed for trajectory inference and fail to fully leverage prior information from upstream analysis, limiting their performance. Here, we introduce scCRT, a novel dimensionality reduction model for trajectory inference. In order to utilize prior information to learn accurate cells representation, scCRT integrates two feature learning components: a cell-level pairwise module and a cluster-level contrastive module. The cell-level module focuses on learning accurate cell representations in a reduced-dimensionality space while maintaining the cell-cell positional relationships in the original space. The cluster-level contrastive module uses prior cell state information to aggregate similar cells, preventing excessive dispersion in the low-dimensional space. Experimental findings from 54 real and 81 synthetic datasets, totaling 135 datasets, highlighted the superior performance of scCRT compared with commonly used trajectory inference methods. Additionally, an ablation study revealed that both cell-level and cluster-level modules enhance the model's ability to learn accurate cell features, facilitating cell lineage inference. The source code of scCRT is available at https://github.com/yuchen21-web/scCRT-for-scRNA-seq.

Most of the existing personalized recommendation methods predict the probability that one user might interact with the next item by matching their representations in the latent space. However, as a cognitive task, it is essential for an impressive recommender system to acquire the cognitive capacity rather than to decide the users' next steps by learning the pattern from the historical interactions through matching-based objectives. Therefore, in this paper, we propose to model the recommendation as a logical reasoning task which is more in line with an intelligent recommender system. Different from the prior works, we embed each query as a box rather than a single point in the vector space, which is able to model sets of users or items enclosed and logical operators (e.g., intersection) over boxes in a more natural manner. Although modeling the logical query with box embedding significantly improves the previous work of reasoning-based recommendation, there still exist two intractable issues including aggregation of box embeddings and training stalemate in critical point of boxes. To tackle these two limitations, we propose a Contrastive Box learning framework for Collaborative Reasoning (CBox4CR). Specifically, CBox4CR combines a smoothed box volume-based contrastive learning objective with the logical reasoning objective to learn the distinctive box representations for the user's preference and the logical query based on the historical interaction sequence. Extensive experiments conducted on four publicly available datasets demonstrate the superiority of our CBox4CR over the state-of-the-art models in recommendation task.

Smart cities are designed to satisfy the needs of residents and improve their quality of life by providing a wide range of smart city services. One of the keys to the efficient operation of smart city services is the accurate forecast of the missing Quality of Service (QoS). Presently, many approaches utilize the context information of users and services, such as geographic location and network location, to somewhat increase the prediction accuracy and forecast the missing QoS values. However, because the network conditions and server status are unpredictable, time is also considered as one of the important factors affecting QoS prediction, which brings more challenges as follows: higher data dimension, more complex data characteristics, and higher data sparsity. To overcome these challenges, we propose an approach for time-aware Web service QoS prediction based on contrastive learning (named CLpred). CLpred utilizes a sequential data input format for QoS data and models these QoS sequences through transformer encoder with CLpred framework. Therefore, it can downscale QoS data and extract a more efficient representation in complex QoS data. Furthermore, it makes it possible to apply data augmentation methods to address the problems of data sparsity. In order to prove the superiority of the proposed approach, particularly inside the presence of extremely high-data sparsity, extensive experiments are conducted on the well-known service QoS data set WSDREAM.

Biomedical Named Entity Recognition (BioNER) aims at identifying biomedical entities such as genes, proteins, diseases, and chemical compounds in the given textual data. However, due to the issues of ethics, privacy, and high specialization of biomedical data, BioNER suffers from the more severe problem of lacking in quality labeled data than the general domain especially for the token-level. Facing the extremely limited labeled biomedical data, this work studies the problem of gazetteer-based BioNER, which aims at building a BioNER system from scratch. It needs to identify the entities in the given sentences when we have zero token-level annotations for training. Previous works usually use sequential labeling models to solve the NER or BioNER task and obtain weakly labeled data from gazetteers when we don't have full annotations. However, these labeled data are quite noisy since we need the labels for each token and the entity coverage of the gazetteers is limited. Here we propose to formulate the BioNER task as a Textual Entailment problem and solve the task via Textual Entailment with Dynamic Contrastive learning (TEDC). TEDC not only alleviates the noisy labeling issue, but also transfers the knowledge from pre-trained textual entailment models. Additionally, the dynamic contrastive learning framework contrasts the entities and non-entities in the same sentence and improves the model's discrimination ability. Experiments on two real-world biomedical datasets show that TEDC can achieve state-of-the-art performance for gazetteer-based BioNER.

With the development of the Industrial Internet of Things system, the huge amount of devices, services, and continuous data, making it difficult to discover a trusted service in complex scenarios. To better leverage knowledge and historical behavior, recommendation systems are applied. However, the model accuracy closely depends on training data size; there is a great risk of data leaking by collecting from multiple departments. To solve these problems, we propose a graph-convolutional-neural-network-based federated approach, which accurately recommends proper service for participating clients without gathering the raw data. Specifically, each client trains locally and uploads the weights of their model to the server for aggregation. Besides, the potential overlapping services of different clients are leveraged to guide the embedding aggregation and sharing, which, in turn, optimize the local training results. Their sensitive scenarios' embedding is kept locally. Owing to the model aggregation, it also resists the poisoning attack to some degree. In addition, the comprehensive experiments on classic public recommendation datasets evaluate the feasibility, effectiveness, trustworthiness, and potential influences.

Recent studies demonstrate that Graph Neural Networks (GNNs) are vulnerable to slight but adversarially designed perturbations, known asadversarial examples. To address this issue, robust training methods against adversarial examples have received considerable attention in the literature.Adversarial Training (AT)is a successful approach to learning a robust model using adversarially perturbed training samples. Existing AT methods on GNNs typically construct adversarial perturbations in terms of graph structures or node features. However, they are less effective and fraught with challenges on graph data due to the discreteness of graph structure and the relationships between connected examples. In this work, we seek to address these challenges and proposeSpectralAdversarialTraining (SAT), a simple yet effective adversarial training approach for GNNs. SAT first adopts a low-rank approximation of the graph structure based on spectral decomposition, and then constructs adversarial perturbations in the spectral domain rather than directly manipulating the original graph structure. To investigate its effectiveness, we employ SAT on three widely used GNNs. Experimental results on four public graph datasets demonstrate that SAT significantly improves the robustness of GNNs against adversarial attacks without sacrificing classification accuracy and training efficiency.

Although some existing models are proposed to exploit reviews for improving performance for recommender systems, few of them can handle the following issues led by the insufficient review data: (i) The regular training process does not exactly fit the scenario of preference prediction with few historical behaviors. (ii) Extracting informative and sufficient semantic features from limited review texts is a challenging work. To alleviate these issues, this paper proposes an enhanced prototypical network, FS-EPN, that leverages reviews for recommendation under the few-shot setting. FS-EPN consists of an attentional prototypical network being the basic architecture, a sentiment encoder and a memory collector cooperating to capture the extra sentimental and collaborative information from both user and item perspectives for semantic information supplement. We train FS-EPN under the meta-learning framework, which models the training process in the episodic manner to mimic the few-shot test environment. Extensive experiments conducted on six publicly available datasets demonstrate the superior capability of FS-EPN over several state-of-the-art models in few-shot recommendation.

Online travel platforms (OTPs), e.g., bookings.com and Ctrip.com, deliver travel experiences to online users by providing travel-related products. Although much progress has been made, the state-of-the-arts for cold-start problems are largely sub-optimal for user representation, since they do not take into account the unique characteristics exhibited from user travel behaviors. In this work, we propose a State-aware Multi-aspect Interests representation Network (SMINet) for cold-start users recommendation at OTPs, which consists of a multi-aspect interests extractor, a co-attention layer, and a state-aware gating layer. The key component of the model is the multi-aspect interests extractor, which is able to extract representations for the user's multi-aspect interests. Furthermore, to learn the interactions between the user behaviors in the current session and the above multi-aspect interests, we carefully design a co-attention layer which allows the cross attentions between the two modules. Additionally, we propose a travel state-aware gating layer to attentively select the multi-aspect interests. The final user representation is obtained by fusing the three components. Comprehensive experiments conducted both offline and online demonstrate the superior performance of the proposed model at user representation, especially for cold-start users, compared with state-of-the-art methods.

Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks. Current methods rely on point clouds from the LiDAR sensor as queries to leverage the feature from the image space. However, people discovered that this underlying assumption makes the current fusion framework infeasible to produce any prediction when there is a LiDAR malfunction, regardless of minor or major. This fundamentally limits the deployment capability to realistic autonomous driving scenarios. In contrast, we propose a surprisingly simple yet novel fusion framework, dubbed BEVFusion, whose camera stream does not depend on the input of LiDAR data, thus addressing the downside of previous methods. We empirically show that our framework surpasses the state-of-the-art methods under the normal training settings. Under the robustness training settings that simulate various LiDAR malfunctions, our framework significantly surpasses the state-of-the-art methods by 15.7% to 28.9% mAP. To the best of our knowledge, we are the first to handle realistic LiDAR malfunction and can be deployed to realistic scenarios without any post-processing procedure.

As the emerging paradigm that is believed to be conducive to the development of intelligent transportation systems (ITS), Internet of Vehicles (IoV) is constructed with a number of connected heterogeneous vehicle devices which provide a variety of services. As the number of vehicle devices in IoV is growing fast, selecting the appropriate service from candidate services which are functionally equivalent is becoming an imperative task. Predicting the non-functional attribute of service invocation, namely quality of service (QoS), to ensure the optimal service selection is the mainstream direction. Considering that most of the conventional prediction methods neglect the fact that QoS values change dynamically with some objective factors, this paper proposes a recurrent neural network based collaborative filtering method called RNCF for QoS prediction. Specifically, a multi-layer GRU structure is incorporated in the framework of neural collaborative filtering to model the dynamic state of physical environments or network conditions and share the invocation records across different time slices. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the proposed QoS prediction model RNCF.

Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy. Specifically, we first introduce six heterogeneous information paths to build our search space, namely top-down, bottom-up, fusing-splitting, scale-equalizing, skip-connect and none. Second, we propose a novel search space of FPNs, in which each FPN candidate is represented by a densely-connected directed acyclic graph (each node is a feature pyramid and each edge is one of the six heterogeneous information paths). Third, we propose an efficient one-shot search method to find the optimal path aggregation architecture; specifically, we first train a super-net and then find the optimal candidate with an evolutionary algorithm. Experimental results demonstrate the efficacy of the proposed OPANAS for object detection: (1) OPANAS is more efficient than state-of-the-art methods (e.g., NAS-FPN and Auto-FPN) at significantly smaller searching cost (e.g., only 4 GPU days on MS-COCO); (2) the optimal architecture found by OPANAS significantly improves main-stream detectors including RetinaNet, Faster R-CNN and Cascade R-CNN, by 2.3∼3.2 % mAP compared to their FPN counterparts; and (3) a new state-of-the-art accuracy-speed trade-off (52.2 % mAP at 7.6 FPS) is achieved at smaller training costs than comparable recent arts. Code will be released at https://github.com/VDIGPKU/OPANAS.

Abstract The unstable link quality in wireless sensor networks (WSNs) directly affects the success rate of data transmission. The retransmission mechanism is one of the commonly used methods to solve this problem. However, too many retransmissions could lower the communication efficiency. Therefore, to reduce retransmissions while guaranteeing the communication reliability in WSNs, this study introduces the NarrowBand Internet of Things (NB‐IoT) technology, and builds a network including both sensor and NB‐IoT nodes. The NB‐IoT node is designed to support both the radio frequency and the NarrowBand communication modes; thus it can communicate with both sensor nodes and NB‐IoT base stations. Further, the communication reliability metrics considering both the link quality and the number of retransmissions in different communication modes are defined, based on which, an adaptive communication reliability algorithm is proposed to switch the communication modes of nodes. The simulation results verify that the proposed algorithm can achieve higher success rate with less end‐to‐end delay and flexibly control the cost on NB‐IoT communication.

With the fast-developing domain of cyber-physical systems (CPS), constructing the CPS with high-quality services becomes an imperative task. As one of the effective solutions for information overload in CPS construction, quality of service (QoS)-aware service recommendation has drawn much attention in academia and industry. However, the lack of most QoS values limits the recommendation performance and it is time-consuming for users to get the QoS values by invoking all the services. Therefore, a powerful prediction model is required to predict the unobserved QoS values. Considering the fact that most existing QoS prediction models are unable to effectively address the data-sparsity problem, a novel two-stage framework called AgQ is proposed for QoS prediction. Specifically, a data augmentation strategy is designed in the first stage to enlarge the training set by drawing additional virtual instances. In the second stage, a prediction model is applied that considers both virtual and factual instances during the training procedure. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the our QoS prediction framework and verify that the data augmentation strategy can indeed alleviate the data-sparsity problem. In terms of mean absolute error, taking the Multilayer Perceptron model as an example, the maximum improvement achieves 5% under 5% sparsity.

In existing CNN based detectors, the backbone network is a very important component for basic feature1 extraction, and the performance of the detectors highly depends on it. In this paper, we aim to achieve better detection performance by building a more powerful backbone from existing ones like ResNet and ResNeXt. Specifically, we propose a novel strategy for assembling multiple identical backbones by composite connections between the adjacent backbones, to form a more powerful backbone named Composite Backbone Network (CBNet). In this way, CBNet iteratively feeds the output features of the previous backbone, namely high-level features, as part of input features to the succeeding backbone, in a stage-by-stage fashion, and finally the feature maps of the last backbone (named Lead Backbone) are used for object detection. We show that CBNet can be very easily integrated into most state-of-the-art detectors and significantly improve their performances. For example, it boosts the mAP of FPN, Mask R-CNN and Cascade R-CNN on the COCO dataset by about 1.5 to 3.0 points. Moreover, experimental results show that the instance segmentation results can be improved as well. Specifically, by simply integrating the proposed CBNet into the baseline detector Cascade Mask R-CNN, we achieve a new state-of-the-art result on COCO dataset (mAP of 53.3) with a single model, which demonstrates great effectiveness of the proposed CBNet architecture. Code will be made available at https://github.com/PKUbahuangliuhe/CBNet.

Mixup (Zhang et al., 2017) is a latest data augmentation technique that linearly interpolates input examples and the corresponding labels.It has shown strong effectiveness in image classification by interpolating images at the pixel level.Inspired by this line of research, in this paper, we explore: i) how to apply mixup to natural language processing tasks since text data can hardly be mixed in the raw format; ii) if mixup is still effective in transformer-based learning models, e.g., BERT.To achieve the goal, we incorporate mixup to transformer-based pre-trained architecture, named "mixup-transformer", for a wide range of NLP tasks while keeping the whole end-to-end training system.We evaluate the proposed framework by running extensive experiments on the GLUE benchmark.Furthermore, we also examine the performance of mixup-transformer in low-resource scenarios by reducing the training data with a certain ratio.Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.

This paper proposes a novel neural network, joint training capsule network (JTCN), for the cold start recommendation task. We propose to mimic the high-level user preference other than the raw interaction history based on the side information for the fresh users. Specifically, an attentive capsule layer is proposed to aggregate high-level user preference from the low-level interaction history via a dynamic routing-by-agreement mechanism. Moreover, JTCN jointly trains the loss for mimicking the user preference and the softmax loss for the recommendation together in an end-to-end manner. Experiments on two publicly available datasets demonstrate the effectiveness of the proposed model. JTCN improves other state-of-the-art methods at least 7.07% for CiteULike and 16.85% for Amazon in terms of [email protected] in cold start recommendation.

In wireless sensor networks, the node reliability can affect the reliability of data transmission. To analyze the node reliability, this paper defines both betweenness centrality and dependency degree for a node to reflect its global reliability and local reliability, respectively. Based on the above definition, a global and local reliability-based routing (GLRR) protocol is proposed to guarantee the reliability of data transmission between a source and destination node in network. In GLRR, at first, some nodes, usually with greater betweenness centrality among their neighbors in a limited range, will be selected as the backtracking node. Moreover, all backtracking nodes then construct their backtracking paths from themselves to the source node separately, and each node on a backtracking path should calculate the dependency degree on its previous hop node. All the betweenness centrality and dependency degree will be forwarded to the source node along the backtracking paths, and be combined to design the routing metric, based on which, the source node can calculate an optimal backtracking path to forward packets to the corresponding backtracking node, meanwhile, this backtracking node will act as a new source node to launch another routing process until the packets be forwarded to the destination node. At last, the simulation results demonstrate that the proposed protocol is superior to the classical algorithms in terms of the network reliability and the network efficiency.

With the explosive growth of services, including Web services, cloud services, APIs and mashups, discovering the appropriate services for consumers is becoming an imperative issue. The traditional service discovery approaches mainly face two challenges: 1) the single source of description documents limits the effectiveness of discovery due to the insufficiency of semantic information; 2) more factors should be considered with the generally increasing functional and nonfunctional requirements of consumers. In this paper, we propose a novel framework, called SMS, for effectively discovering the appropriate services by incorporating social media information. Specifically, we present different methods to measure four social factors (semantic similarity, popularity, activity, decay factor) collected from Twitter. Latent Semantic Indexing (LSI) model is applied to mine semantic information of services from meta-data of Twitter Lists that contains them. In addition, we assume the target query-service matching function as a linear combination of multiple social factors and design a weight learning algorithm to learn an optimal combination of the measured social factors. Comprehensive experiments based on a real-world dataset crawled from Twitter demonstrate the effectiveness of the proposed framework SMS, through some compared approaches.

With the rapid development of mobile apps, the availability of a large number of mobile apps in application stores brings challenges to locate appropriate apps for users. Providing accurate mobile app recommendation for users becomes an imperative task. Conventional approaches mainly focus on learning users' preferences and app features to predict the user-app ratings. However, most of them did not consider the interactions among the context information of apps. To address this issue, we propose a broad learning approach for Context-Aware app recommendation with Tensor Analysis (CATA). Specifically, we utilize a tensor-based framework to effectively integrate app category information and multi-view features on users and apps, respectively, to facilitate the performance of rating prediction. The multidimensional structure is employed to capture the hidden relationships among the app categories and the multiview features. We develop an efficient factorization method which applies Tucker decomposition to learn the full-order interactions among the app categories and features. Furthermore, we employ a group ℓ1-norm regularization to learn the group-wise feature importance of each view with respect to each app category. Experiments on a real-world mobile app dataset demonstrate the effectiveness of the proposed method.

With the proliferation of mobile application (app) markets (e.g., Google Play, Apple App Store), predicting user preferences on apps becomes a challenging problem. Different from previous work, we assume that a user likes an app because he/she likes certain features of the app (e.g., permission, genre, topic). Based on this assumption, we propose a feature-oriented approach to predict user preferences on apps. Specifically, we transform the original app rating matrix to feature rating data and predict the unknown ratings on the features through a latent factor model, instead of directly predicting ratings on apps. The predicted user ratings on features can be used to generate the ratings on apps. Two integration methods are presented to give different significance for feature preferences. The approach has some obvious advantages: as it integrates feature information to analyze the details of user preference, it can generalize better as the feature rating data is denser, and improve the interpretation of the prediction of app ratings. Experimental results on a real-world dataset demonstrate the effectiveness of the proposed approach.

As web-enabled software becomes the standard for business processes, the ways organizations, partners and customers interface with it have become a critical differentiator in the market place, i.e., API Economy. With the rapid proliferation of APIs, it is increasingly important for users to effectively manage objective APIs in kinds of API markets, e.g., ProgramableWeb (PW), Mashape, etc. In this paper, to facilitate the process of API management, we propose a graphbased recommendation approach called ATRec to automatically assign tags to unlabeled APIs by exploiting both graph structure information and semantic similarity. Specifically, ATRec first leverages the multi-type relations (i.e., among APIs, mashups, and mashup assigned tags) to construct a heterogeneous network, in which a Random Walk with Restart (RWR) model is applied to alleviate the total cold start problem where no API has ever been tagged. Furthermore, we apply the recommended API tags in two API management scenarios (API search, API recommendation). Comprehensive experiments based on a real dataset crawled from PW demonstrate the effectiveness of the proposed approach.

In this paper, we propose an ant colony-based direct communication model routing (AntDMR) algorithm aimed at wireless emergency communication system. When network infrastructure is destroyed, direct communication mode is employed for guaranteeing system availability. Accordingly, the selection of effective transmission path is a key problem. Considering delay, energy consumption and pheromone track model, the next hop node selection probability function is redefined. Furthermore, the optimal route is achieved. Finally, by comparing with traditional routing algorithm, the performance is impoved more in AntDMR from time-delay and energy-efficiency perspective.

In order to let people be able to get information from the Web easily, search engine comes into being and continues to grow and develop. People begin to explore all kinds of ranking algorithms and try to give user a good result list. However, the expression format of the web information and user queries are very simple, which results in the difficulty of determining the relevance between user queries and web information. The success and popularity of social network systems, such as del.icio.us, Face book, etc., have generated many interesting problems to the research community. This gives us a new viewpoint on how to improve the quality of information retrieval. The contributions of our research are twofold. First, the existing ranking algorithms of search engine are classified. And we extend expression of queries by “keyword and ”, instead of keywords only. Second, a new ranking algorithm based on user feedback and semantic tags is proposed, and it is also compared with Google by several evaluation methods.