Weight normalization optimization movie recommendation algorithm based on three-way neural interaction networks

Abstract

Heterogeneous information networks are increasingly used in recommendation algorithms. However, they lack an explicit representation of meta-paths. In using bidirectional neural interaction models for recommendation models, interaction between users and items is often ignored, with an integral impact on the accuracy of the recommendations. To better apply the interaction information, this study proposes a weight-normalized movie recommendation model (SCLW_MCRec) based on a three-way neural interaction network. The model constructs a three-way neural interaction network $$\langle $$ ⟨ user, meta-path, item$$\rangle $$ ⟩ from meta-path contextual information, introducing meta-paths on top of the user-item representation to represent the user-item interaction information. Introduction of a two-layer, one-dimensional convolutional neural network helps capture higher-order interaction features between the user and the item, making the model more powerful in terms of interaction. Adding a dropout layer to the interaction model and using a two-layer convolutional neural network can prevent overfitting and discard irrelevant information features to improve the recommendation. In addition, an extreme cross-entropy loss (argmaxminloss) that incorporates the properties of the argmin and argmax functions is designed to reduce the model loss. A weight-normalization optimization approach is used to better optimize the model and accelerate convergence of the stochastic gradient descent optimization. Compared to current state-of-the-art recommendation models, the SCLW_MCRec model improves the Prec evaluation index by 2.94–35.8%, Recall by 1.15–53.51%, and NDCG by 6.7–49.37% on the MovieLens dataset. The framework provides a significant improvement in recommendation accuracy and also solves the cold-start problem with application of interaction information.

Systematic Literature Review on Recommender System: Approach, Problem, Evaluation Techniques, Datasets

“…[75], [67], [81], [42], [68], [44], [82], [23], [45], [83], [31], [13], [77], [1], [35], [46], [47], [48], [14], [69], [74], [72], [51], [52], [88], [85], [87] Normalized Discounted Cumulative Gain (NDCG) 𝑁𝐷𝐶𝐺@𝐾 = 𝐷𝐶𝐺@𝑘 𝐼𝐷𝐶𝐺@𝐾 [7], [67], [22], [40], [70], [49], [76], [6], [89], [90], [91], [92] Precision 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛(𝑢) = [39], [81], [22], [28], [12], [48], [76], [71], [89], [36], [97], [95], [98], [92...…”

“…|𝑅𝑒𝑐𝑜𝑚𝑚𝑒𝑛𝑑𝑒𝑑(𝑢)∩𝑇𝑒𝑠𝑡𝑖𝑛𝑔(𝑢)| |𝑅𝑒𝑐𝑜𝑚𝑚𝑒𝑛𝑑𝑒𝑑(𝑢)|[48],[49],[71],[72],[90],[93],[85],[94],[87] Recall 𝑅𝑒𝑐𝑎𝑙𝑙(𝑢) =|𝑅𝑒𝑐𝑜𝑚𝑚𝑒𝑛𝑑𝑒𝑑(𝑢)∩𝑇𝑒𝑠𝑡𝑖𝑛𝑔(𝑢)| |𝑇𝑒𝑠𝑡𝑖𝑛𝑔(𝑢)|[48],[70],[71],[72],[52],[6],[90],[95],[96],[85], [87, Hit Ratio (HR), the MOABC and NSGA-II, etc.…”