Resource Recommendation Based on Industrial Knowledge Graph in Low-Resource Conditions

Abstract

Resource recommendation is extremely challenging under low-resource conditions because representation learning models require sufficient triplets for their training, and the presence of massive long-tail resources leads to data sparsity and cold-start problems. In this paper, an industrial knowledge graph is developed to integrate resources for manufacturing enterprises, and we further formulate long-tail recommendations as a few-shot relational learning problem of learning-to-recommend resources with few interactions under low-resource conditions. First, an industrial knowledge graph is constructed based on the predesigned resource schema. Second, we conduct schema-based reasoning on the schema to heuristically complete the knowledge graph. At last, we propose a multi-head attention-based meta relational learning model with schema-based reasoning to recommend long-tail resources under low-resource conditions. With the IN-Train setting, 5-shot experimental results on the NELL-One and Wiki-One datasets achieve average improvements of 28.8 and 13.3% respectively, compared with MetaR. Empirically, the attention mechanism with relation space translation learns the most important relations for fast convergence. The proposed graph-based platform specifies how to recommend resources using the industrial knowledge graph under low-resource conditions.

Healthy Food Recommendation Using a Time-Aware Community Detection Approach and Reliability Measurement

“…Accordingly, users' ratings, food nutrition, and timestamps are crawled for each food. The ratings assigned to foods by users are in the range of [1,5] where the rating score of 1 for a food indicates that the user has no interest in this food, while the rating score of 5 shows the highest interest. The rating of a variety of foods is used to generate implicit feedback, indicating whether the users interacted with foods.…”

“…Internet and mobile technologies make it possible for people to access information anytime and anywhere [1][2][3]. People's lifestyles have been intensively altered by online systems, including social media, e-commerce, and different lifestyle application [4][5][6][7]. When friends get together for dinner, they might share pictures of the food they enjoy on social media, and users might turn to apps for recommendations when deciding what to eat [8][9][10].…”

Theory and Practice of Constructing College Physical Education Curricula Based on Immersive Multimedia Technology

“…Utilizing online resources in physical education maximizes student engagement, transforming them from mere recipients of knowledge to proactive seekers. This shift facilitates a transition from passive to active learning (Liu et al, 2022). Such an adaptable learning process fosters students' abilities in self-management and independent learning.…”

Graph-enabled digital twins for intelligent product lifecycle management: a multi-dimensional approach to design, manufacturing, and supply chain transformation

“…Lv et al [165] exploited the KGE technique to predict top-N procurement records related to purchase demands, thereby recommending suppliers with a remarkable performance. Liu et al [363] developed an iKG in low-resource conditions to recommend resources to cooperative suppliers.…”

“…Extant graph-enabled methods can also identify reliable and cost-effective suppliers via graph-based approaches, leading to improved efficiency and cost savings during disruptions [379]. Specifically, KG-based decision support systems, which analyses the connectivity and attributes of domain-specific workflows and processes, has received much attention in academia Chapter 2 Literature Review 91 [363]. Wang et al [380] developed graph attention networks for accurate and explainable recommendations.…”