Multi-behavior recommendation models excel in extracting abundant information from user-item interactions to enhance performance; however, they encounter challenges in accuracy due to noise disturbance and ambiguous weight allocation. In this paper, we propose cd-MBRec, a novel model designed to amplify commonality among various behaviors, thereby minimizing noise interference while preserving behavior diversity to highlight semantic variations in feedback across distinct scenarios. Specifically, the model begins by constructing behavior matrices that models separate behaviors, along with an interaction matrix offering a broad overview of user behaviors. It employs graph neural networks to extract higher-order semantic and structural information from input data. Concurrently, the model integrates principles of Weber-Fechner Law for the adaptive allocation of initial weights to the multiple behaviors and utilizes matrix factorization techniques for efficient behavior embedding. Extensive experiments on two real-world datasets demonstrate that cd-MBRec surpasses existing state-of-the-art models in recommendation performance, achieving notable average improvements of 4.96% in HR@10 and 7.75% in NDCG@10.

Composed image retrieval is designed to more accurately retrieve target images that align with user intentions by using a combination of reference images and descriptive modification texts. However, existing methods primarily focus on designing complex feature fusion networks while neglecting the prevalent issues of noise and inconsistent sample quality in training data, leading to insufficient cross-modal semantic alignment and sample relevance modeling. To address this, we propose an innovative Tripartite Alignment Network (TAN) that introduces a momentum distillation mechanism, leveraging the historical knowledge of a teacher network as additional super-vision to guide the optimization of the student network. During the feature encoder fine-tuning stage, we design response-based knowledge distillation and feature-based knowledge distillation techniques, explicitly strengthening modal alignment through composed-target contrastive learning and implicitly promoting modal fusion via composed-target matching learning. In the combiner training stage, we incorporate a lightweight combiner network and employ a cross-entropy-based matching loss function, encouraging high matching scores for relevant image-text pairs and low scores for irrelevant pairs. Extensive experiments on the FashionIQ and Shoes datasets demonstrate that TAN exhibits superior performance compared to existing state-of-the-art methods, with notable improvements in R@10 of +14.03% and +13.09%, respectively. These results affirm the effectiveness of momentum distillation in multimodal learning. Access the source code at https://github.com/Maserhe/TAN.

Extracting more information from feature interactions is essential to improve click-through rate (CTR) prediction accuracy. Although deep learning technology can help capture high-order feature interactions, the combination of features lacks interpretability. In this paper, we propose a multi-semantic feature interaction learning network (MeFiNet), which utilizes convolution operations to map feature interactions to multi-semantic spaces to improve their expressive ability and uses an improved Squeeze & Excitation method based on SENet to learn the importance of these interactions in different semantic spaces. The Squeeze operation helps to obtain the global importance distribution of semantic spaces, and the Excitation operation helps to dynamically re-assign the weights of semantic features so that both semantic diversity and feature diversity are considered in the model. The generated multi-semantic feature interactions are concatenated with the original feature embeddings and input into a deep learning network. Experiments on three public datasets demonstrate the effectiveness of the proposed model. Compared with state-of-the-art methods, the model achieves excellent performance (+0.18% in AUC and -0.34% in LogLoss VS DeepFM; +0.19% in AUC and -0.33% in LogLoss VS FiBiNet).

Fashion image retrieval is one of the important services of e-commerce platforms, and it is also the basis of various fashion-related AI applications. Studies have shown that in a multi-modal environment (images + attribute labels), embedding items into specific attribute spaces can support more fine-grained similarity measures, which is especially suitable for fashion retrieval tasks. In this paper, we propose an attention-based attribute-guided similarity learning network (AttnFashion) for fashion image retrieval. The core of this network is an attribute-guided spatial attention module and an attribute-guided channel attention module, which correspond to the mapping between attributes and image regions, and the mapping between attributes and high-level image semantics, respectively. To make these two modules interact deeply, we design a parallel structure that allows them to share attribute embeddings and guide each other to extract specific features, which also helps to reduce the network parameters of the attention modules. An adaptive feature fusion strategy is proposed to synthesise the features extracted by the two modules. Extensive experiments show that the proposed AttnFashion performs better than current competitive networks in the field of fine-grained attribute-based fashion retrieval.

Learning the similarity between fashion items is essential for many fashion-related tasks. Most methods based on global or local image similarity cannot meet the fine-grained retrieval requirements related to attributes. We are the first to clearly distinguish the concepts of attribute name and their values and divide fashion retrieval tasks that combine images and text into: attribute-guided retrieval and attribute-manipulated retrieval. We propose a hierarchical attribute-aware embedding network (HAEN) that takes images and attributes as input, learns multiple attribute-specific embedding spaces, and measures fine-grained similarity in the corresponding spaces. It can accurately map different attributes to the corresponding areas of the image, thereby facilitating the feature fusion of two different modalities of text and image, including enhancement and replacement. Then on this basis, we propose three attribute-manipulated similarity learning methods, HAEN_Avg, HAEN_Rec, and HAEN_Cmb. With comprehensive validation on two real-world fashion datasets, we demonstrate that our methods can effectively leverage semantic knowledge to improve image retrieval performance, including attribute-guided and attribute-manipulated retrieval tasks.

Image retrieval methods in the fashion field mainly take advantage of query images that reflect user needs, without considering additional keywords that users can provide to specify the attributes in their interests. To achieve the fine-grained fashion retrieval, we propose an iterative similarity learning network (ISLN) for attribute-guided image retrieval, which takes a query image and a specified attribute as input, and outputs other images with the same or similar attribute values. The core of the network is the iterative similarity learning module, which leverages the aggressive learning ability of the deep neural network (DNN) to focus on the area of interest and extract a more accurate feature embedding during the learning process of image and text semantic mapping. Extensive experiments on FashionAI and DARN (+8.33% and +10.73% in mAP) datasets show that ISLN performs better than the state-of-the-art methods in fine-grained similarity retrieval tasks.

Recommender systems still face a trade-off between exploring new items to maximize user satisfaction and exploiting those already interacted with to match user interests. This problem is widely recognized as the exploration/exploitation (EE) dilemma, and the multi-armed bandit (MAB) algorithm has proven to be an effective solution. As the scale of users and items in real-world application scenarios increases, their purchase interactions become sparser. Then three issues need to be investigated when building MAB-based recommender systems. First, large-scale users and sparse interactions increase the difficulty of user preference mining. Second, traditional bandits model items as arms and cannot deal with ever-growing items effectively. Third, widely used Bernoulli-based reward mechanisms only feedback 0 or 1, ignoring rich implicit feedback such as behaviors like click and add-to-cart. To address these problems, we propose an algorithm named Dynamic Clustering based Contextual Combinatorial Multi-Armed Bandits (DC3MAB), which consists of three configurable key components. Specifically, a dynamic user clustering strategy enables different users in the same cluster to cooperate in estimating the expected rewards of arms. A dynamic item partitioning approach based on collaborative filtering significantly reduces the scale of arms and produces a recommendation list instead of one item to provide diversity. In addition, a multi-class reward mechanism based on fine-grained implicit feedback helps better capture user preferences. Extensive empirical experiments on three real-world datasets demonstrate the superiority of our proposed DC3MAB over state-of-the-art bandits (On average, +75.8% in F1 and +54.3% in cumulative reward). The source code is available at https://github.com/HaixHan/DC3MAB.

Sales forecasting is an important part of e-commerce and is critical to smart business decisions. The traditional forecasting methods mainly focus on building a forecasting model, training the model through historical data, and then using it to forecast future sales. Such methods are feasible and effective for the products with rich historical data while they are not performing as well for the newly listed products with little or no historical data. In this paper, with the idea of collaborative filtering, a similarity-based sales forecasting (S-SF) method is proposed. The implementation framework of S-SF includes three modules in order. The similarity module is responsible for generating top-k similar products of a given new product. We calculate the similarity based on two data types: time series data of sales and text data such as product attributes. In the learning module, we propose an attention-based ConvLSTM model which we called AttConvLSTM, and optimize its loss function with the convex function information entropy. Then AttConvLSTM is integrated with Facebook Prophet model to forecast top-k similar products sales based on their historical data. The prediction results of all top-k similar products will be fused in the forecasting module through operations of alignment and scaling to forecast the target products sales. The experimental results show that the proposed S-SF method can simultaneously adapt to the sales forecasting of mature products and new products, which shows excellent diversity, and the forecasting idea based on similar products improves the accuracy of sales forecasting.

Matrix factorization (MF) models are effective and easy to expand and are widely used in industry, such as rating prediction and item recommendation. The basic MF model is relatively simple. In practical applications, side information such as attributes or implicit feedback is often combined to improve accuracy by modifying the model and optimizing the algorithm. In this paper, we propose an attribute interaction-aware matrix factorization (AIMF) method for recommendation tasks. We partition the original rating matrix into different sub-matrices according to the attribute interactions, train each sub-matrix independently, and merge all the latent vectors to generate the final score. Since the generated sub-matrices vary in size, an adaptive regularization coefficient optimization strategy and an adaptive latent vector dimension optimization strategy are proposed for sub-matrix training, and a variety of latent vector merging methods are put forward. The method AIMF has two advantages. When the original rating matrix is particularly large, the training time complexity of the MF-based model becomes higher and the update cost of the model is also higher. In AIMF, because each sub-matrix is usually much smaller than the original rating matrix, the training time complexity is greatly reduced after using parallel computing technology. Secondly, in AIMF, it is not necessary to modify the matrix factorization model to incorporate attributes and their interactive information into the model to improve the performance. The experimental results on the two classic public datasets MovieLens 1M and MovieLens 100k show that AIMF can not only effectively improve the accuracy of recommendation, but also make full use of parallel computing technology to improve training efficiency without modifying the matrix factorization model.