Effective feature interaction modeling is critical for enhancing the accuracy of click-through rate (CTR) prediction in industrial recommender systems. Most of the current deep CTR models resort to building complex network architectures to better capture intricate feature interactions (FIs) or user behaviors. However, we identify two limitations in these models: 1) the samples given to the model are undifferentiated, which may lead the model to learn a larger number of easy samples in a single-minded manner while ignoring a smaller number of hard samples, thus reducing the model’s generalization ability; and 2) differentiated FI encoders are designed to capture different interactions information but receive consistent supervision signals, thereby limiting the effectiveness of the encoder. To bridge the identified gaps, this article introduces a novel CTR prediction framework by integrating the plug-and-playTwin Focus (TF) Loss,Sample Selection Embedding Module (SSEM), andDynamic Fusion Module (DFM), named the TF Framework for CTR (TF4CTR). Specifically, the framework employs the SSEM at the bottom of the model to differentiate between samples, thereby assigning a more suitable encoder for each sample. Meanwhile, the TF Loss provides tailored supervision signals to both simple and complex encoders. Moreover, the DFM dynamically fuses the FI information captured by the encoders, resulting in more accurate predictions. Experiments on five real-world datasets confirm the effectiveness and compatibility of the framework, demonstrating its capacity to enhance various representative baselines in a model-agnostic manner.

Click-through rate (CTR) prediction plays a pivotal role in recommender systems and online advertising by estimating the probability of user engagement with recommended items or advertisements. However, existing methodologies encounter multiple challenges. First, current approaches often struggle to maintain robustness in the presence of noise. This challenge arises from the inherent complexity of real-world data, where noisy or irrelevant features can significantly impact model performance. Second, while existing models may achieve high accuracy, their inner workings are often lacking in interpretability, hindering users’ comprehension of the reasoning behind specific predictions. Third, conventional complex model architectures often suffer from the issue of excessive parameterization, which can be unacceptable when dealing with large-scale datasets, potentially leading to computational inefficiencies. In this study, we present information bottleneck deep cross network (IBNet) with the mice activation function to address these challenges. IBNet leverages the information bottleneck principle with contrastive learning to adaptively filter noise in high-order feature interactions, while mice ensure full information flow and prevents over-parameterization. Additionally, this article provides interpretability from the perspective of invariable and variable factors. Comprehensive experiments on four datasets demonstrate IBNet’s robustness, interpretability, and parameter efficiency, with mice proving beneficial across diverse deep learning CTR models.

Large language models (LLMs) have seen rapid improvement in the recent years, and have been used in a wider range of applications. After being trained on large text corpus, LLMs obtain the capability of extracting rich features from textual data. Such capability is potentially useful for the web service recommendation task, where the web users and services have intrinsic attributes that can be described using natural language sentences and are useful for recommendation. In this paper, we explore the possibility and practicality of using LLMs for web service recommendation. We propose the large language model aided QoS prediction (llmQoS) model, which use LLMs to extract useful information from attributes of web users and services via descriptive sentences. This information is then used in combination with the QoS values of historical interactions of users and services, to predict QoS values for any given user-service pair. On the WSDream dataset, llmQoS is shown to overcome the data sparsity issue inherent to the QoS prediction problem, and outperforms comparable baseline models consistently.

Social recommendation leverages social network to complement user–item interaction data for recommendation task, aiming to mitigate the data sparsity issue in recommender systems. The information propagation mechanism of graph neural networks (GNNs) aligns well with the process of social influence diffusion in social network, thereby can theoretically boost the performance of recommendation. However, existing social recommendation methods encounter the following challenge: both social network and interaction data contain substantial noise, and the propagation of such noise through GNNs not only fails to enhance recommendation performance but may also interfere with the model’s normal training. However, despite the importance of denoising for social network and interaction data, only a limited number of studies have considered the denoising for social network and all of them overlook that for interaction data, hindering the denoising effect and recommendation performance. Based on this, we propose a novel model called dual-domain collaborative denoising for social recommendation (DCDSR). DCDSR comprises two primary modules: the structure-level collaborative denoising module and the embedding-space collaborative denoising module. In the structure-level collaborative denoising module, information from the interaction domain is first employed to guide social network denoising. Subsequently, the denoised social network is used to supervise the denoising of interaction data. The embedding-space collaborative denoising module devotes to resisting the noise cross-domain diffusion problem through contrastive learning with dual-domain embedding collaborative perturbation. Additionally, a novel contrastive learning strategy, named Anchor-InfoNCE, is introduced to better harness the denoising capability of contrastive learning. The model is jointly trained under a recommendation task and a contrastive learning task. Evaluating our model on three real-world datasets verifies that DCDSR has a considerable denoising effect, thus outperforms the state-of-the-art social recommendation methods.

Click-through rate (CTR) prediction is a crucial task in personalized information retrievals, such as industrial recommender systems, online advertising, and web search. Most existing CTR Prediction models utilize explicit feature interactions to overcome the performance bottleneck of implicit feature interactions. Hence, deep CTR models based on parallel structures (e.g., DCN, FinalMLP, xDeepFM) have been proposed to obtain joint information from different semantic spaces. However, these parallel subcomponents lack effective supervision and communication signals, making it challenging to efficiently capture valuable multi-views feature interaction information in different semantic spaces. To address these issues, we propose a simple yet effective novel CTR model: Contrast-enhanced Through Network (CETN). Drawing inspiration from sociology, CETN leverages the complementary nature of diversity and homogeneity to guide the model in acquiring higher-quality feature interaction information. Specifically, CETN employs product-based feature interactions and the augmentation (perturbation) concept from contrastive learning to segment different semantic spaces, each with distinct activation functions. This improves diversity in the feature interaction information captured by the model. Additionally, we introduce self-supervised signals and through connection within each semantic space to ensure the homogeneity of the captured feature interaction information. The experiments conducted on four real datasets demonstrate that our model consistently outperforms twenty baseline models in terms of AUC and Logloss.

The goal of click-through rate (CTR) prediction in recommender systems is to effectively work with input features. However, existing CTR prediction models face three main issues. First, many models use a basic approach for feature combinations, leading to noise and reduced accuracy. Second, there is no consideration for the varying importance of features in different interaction orders, affecting model performance. Third, current model architectures struggle to capture different interaction signals from various semantic spaces, leading to sub-optimal performance. To address these issues, we propose the Adaptive Graph Interaction Network (AdaGIN) with the Graph Neural Networks-based Feature Interaction Module (GFIM), the Multi-semantic Feature Interaction Module (MFIM), and the Negative Feedback-based Search (NFS) algorithm. GFIM explicitly aggregates information between features and assesses their importance, while MFIM captures information from different semantic spaces. NFS uses negative feedback to optimize model complexity. Experimental results show AdaGIN outperforms existing models on large-scale public benchmark datasets.

Click-through rate (CTR) prediction is an essential component of industrial multimedia recommendation, and the key to enhancing the accuracy of CTR prediction lies in the effective modeling of feature interactions using rich user profiles, item attributes, and contextual information. Most of the current deep CTR models resort to parallel or stacked structures to break through the performance bottleneck of Multi-Layer Perceptron (MLP). However, we identify two limitations in these models: (1) parallel or stacked structures often treat explicit and implicit components as isolated entities, leading to a loss of mutual information; (2) traditional CTR models, whether in terms of supervision signals or interaction methods, lack the ability to filter out noise information, thereby limiting the effectiveness of the models.

Pancreatic cancer is a globally recognized highly aggressive malignancy, posing a significant threat to human health and characterized by pronounced heterogeneity. In recent years, researchers have uncovered that the development and progression of cancer are often attributed to the accumulation of somatic mutations within cells. However, cancer somatic mutation data exhibit characteristics such as high dimensionality and sparsity, which pose new challenges in utilizing these data effectively. In this study, we propagated the discrete somatic mutation data of pancreatic cancer through a network propagation model based on protein-protein interaction networks. This resulted in smoothed somatic mutation profile data that incorporate protein network information. Based on this smoothed mutation profile data, we obtained the activity levels of different metabolic pathways in pancreatic cancer patients. Subsequently, using the activity levels of various metabolic pathways in cancer patients, we employed a deep clustering algorithm to establish biologically and clinically relevant metabolic subtypes of pancreatic cancer. Our study holds scientific significance in classifying pancreatic cancer based on somatic mutation data and may provide a crucial theoretical basis for the diagnosis and immunotherapy of pancreatic cancer patients.

Defects on the surface of fabrics seriously affect the production speed and quality of textile products. There are many difficulties in the detection of surface defects on fabrics, such as substantial differences in length-width ratio, uneven distribution, and few features. However, existing methods have the disadvantages of slow detection speed and high misdetection rate. This present study proposes a method of integrating deformable convolution and pyramid network in Cascade R-CNN (IDPNet) for fabric defect detection. First, image data are labeled according to the type and distribution of defects. Then we design a novel multi-stage object detection architecture named IDPNet to detect defects on the surface of fabrics. In the first stage, Resnet50, in combination with feature pyramid network and deformable convolution is used to improve the detection performance of small defects. Besides, we trained a sequence of detectors with increasing IoUs stage by stage based on Cascade R-CNN in the second stage. Finally, experimental results demonstrate that the proposed neural network equip an outstanding performance against other approaches and achieve the accuracy of 91.57% in fabric defect detection, which proves its utility in practice.

Citrus detection is an essential component of the citrus industry. In order to realize the identification, positioning, segmentation, maturity estimation, and quality evaluation of citrus in complex environments, this paper proposes a multi-task deep learning network that can be applied to multiple scenes for citrus detection. The system is based on the Mask R-CNN network framework. By adding multi-task branches, modifying model parameters, and designing multi-task loss function, it can realize multi-task detection of citrus in a complex environment. The mAP on the validation set of the model obtained after training is 91.56%, and it takes an average of 0.35s to detect a citrus image using GeForce GTX 1080 Ti. Through the comparative analysis of the detection effect and performance evaluation index F value of multi-task citrus under different maturity, quality, citrus quantity, and light angle, the experimental results show that the model can effectively and accurately detect the citrus with different maturity and quality in the environment of citrus fruit overlap, tree branch and leaf occlusion, light change and surface shadow. The code is available at https://github.com/wxx-gan/Multitask.

We consider constraint-based methods for causal structure learning, such as the PC algorithm or any PC-derived algorithms whose first step consists in pruning a complete graph to obtain an undirected graph skeleton, which is subsequently oriented. All constraint-based methods perform this first step of removing dispensable edges, iteratively, whenever a separating set and corresponding conditional independence can be found. Yet, constraint-based methods lack robustness over sampling noise and are prone to uncover spurious conditional independences in finite datasets. In particular, there is no guarantee that the separating sets identified during the iterative pruning step remain consistent with the final graph. In this paper, we propose a simple modification of PC and PC-derived algorithms so as to ensure that all separating sets identified to remove dispensable edges are consistent with the final graph,thus enhancing the explainability of constraint-basedmethods. It is achieved by repeating the constraint-based causal structure learning scheme, iteratively, while searching for separating sets that are consistent with the graph obtained at the previous iteration. Ensuring the consistency of separating sets can be done at a limited complexity cost, through the use of block-cut tree decomposition of graph skeletons, and is found to increase their validity in terms of actual d-separation. It also significantly improves the sensitivity of constraint-based methods while retaining good overall structure learning performance. Finally and foremost, ensuring sepset consistency improves the interpretability of constraint-based models for real-life applications.