MDPI - Publisher of Open Access Journals

20 pages, 3684 KB

Open AccessArticle

Recommendation Algorithm for Multi-Task Learning with Directed Graph Convolutional Networks

by Lifeng Yin, Jianzheng Lu, Guanghai Zheng, Huayue Chen and Wu Deng

Appl. Sci. 2022, 12(18), 8956; https://doi.org/10.3390/app12188956 - 6 Sep 2022

Cited by 3 | Viewed by 2537

As an important branch of machine learning, recommendation algorithms have attracted the attention of many experts and scholars. The current recommendation algorithms all more or less have problems such as cold start and single recommended items. In order to overcome these problems and improve the accuracy of personalized recommendation algorithms, this paper proposes a recommendation for multi-task learning based on directed graph convolutional network (referred to as MTL-DGCNR) and applies it to recommended areas for e-commerce. First, the user’s micro-behavior is constructed and converted into directed graph structure data for model embedding. It can fully consider the embedding of first-order proximity nodes and second-order proximity nodes, which can effectively enhance the transformation ability of features. Secondly, this model adopts the multi-task learning method, and uses knowledge graph embedding to effectively deal with the one-to-many or many-to-many relationship between users and commodities. Finally, it is verified by experiments that MTL-DGCNR has a higher interpretability and accuracy in the field of e-commerce recommendation than other recommendation models. The ranking evaluation experiments, various training methods comparison experiments, and controlling parameter experiments are designed from multiple perspectives to verify the rationality of MTL-DGCNR. Full article

(This article belongs to the Special Issue Soft Computing Application to Engineering Design)

► Show Figures

Figure 1

18 pages, 2662 KB

Open AccessArticle

The Systematic Optimization of Train Formation in Loading Stations

by Boliang Lin and Yinan Zhao

Symmetry 2019, 11(10), 1238; https://doi.org/10.3390/sym11101238 - 3 Oct 2019

Cited by 7 | Viewed by 2761

Abstract

This paper presents the formulation of a train formation problem in rail loading stations (TFLS) from the systematic perspective. Several patterns of train formation are analyzed thoroughly before modeling, including direct single-commodity trains, direct multi-commodity trains created in the loading stations, and direct trains originating from reclassification yards. One of the crucial preconditions is that the loading and unloading efficiencies in the loading stations and the relational unloading stations are symmetric. Based on this, a non-linear 0–1 programming model is designed with the aim of minimizing the total car-hour cost incurred by the loading, unloading, and reclassification operations, and the commercial software Lingo is employed as the solving approach. A small-scale example is carried out first to illustrate the validity of the presented model and the effectiveness of the proposed method. Then, a series of numerical cases are devised to test the model and solving approach. The computational results show that our model can be regarded as a theoretical foundation of the TFLS problem. Full article

► Show Figures

Graphical abstract

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI