Graph Neural Network
Assembly Line
Manufacturing service capability prediction with Graph Neural Networks
In the current landscape, the predominant methods for identifying manufacturing capabilities from manufacturers rely heavily on keyword matching and semantic matching. However, these methods often fall short by either overlooking valuable hidden information or misinterpreting critical data. Consequently, such approaches result in an incomplete identification of manufacturers’ capabilities. This underscores the pressing need for data-driven solutions to enhance the accuracy and completeness of manufacturing capability identification. To address the need, this study proposes a Graph Neural Network-based method for manufacturing service capability identification over a knowledge graph. To enhance the identification performance, this work introduces a novel approach that involves aggregating information from the graph nodes’ neighborhoods as well as oversampling the graph data, which can be effectively applied across a wide range of practical scenarios. Evaluations conducted on a Manufacturing Service Knowledge Graph and subsequent ablation studies demonstrate the efficacy and robustness of the proposed approach. This study not only contributes a innovative method for inferring manufacturing service capabilities but also significantly augments the quality of Manufacturing Service Knowledge Graphs.
Your supplier’s supplier is not your supplier – Graph learning for transparency in deep-tier supply networks
Early graph neural networks have been applied to supply network data, but these are not as accurate as they could be because they focus only on supplier-buyer relationships and assume each company only produces one type of product. As a result, most companies with various types of products still lack visibility into risks involving deep-tier suppliers.
In this blog, we propose a graph representation learning method that models supply networks as heterogeneous graphs. The benefit of this model is that it can depict multiple relationships between companies and products, thus exposing the deep-tier supplier risk of companies with multiple products.
For companies within increasingly complicated supply networks, risk exposure extends far beyond direct suppliers. However, most companies lack risk transparency into their deep-tier supply networks because the supplier of their supplier is not their deep-tier supplier.
🧠 This Neural Net Maps Molecules to Aromas
Using a type of deep-learning algorithm called a graph neural network, researchers have built a model that maps chemical structure to odor descriptors. The model has successfully predicted how a panel of humans would describe new smells, and it could be an important step along a long path toward digitizing smells.
The model used a specific type of graph neural network called a message-passing neural network. It was trained on a combined fragrance industry dataset of over 5,000 molecules with their structures converted into graphs and tagged with professional odor notes. Part of the research group worked at Google when the work began, and a few have since formed an offshoot company, Osmo, in January 2023, supported by Google Ventures, Alphabet’s venture capital arm.
Using graph neural networks to recommend related products
In experiments, we found that our approach outperformed state-of-the-art baselines by 30% to 160%, as measured by HitRate and mean reciprocal rank, both of which compare model predictions to actual customer co-purchases. We have begun to deploy this model in production.
The main difficulty with using graph neural networks (GNNs) to do related-product recommendation is that the relationships between products are asymmetric. It makes perfect sense to recommend a phone case to someone who’s buying a new phone but less sense to recommend a phone to someone who’s buying a case. We solve this problem by producing two embeddings of every graph node: one that characterizes its role as the source of a related-product recommendation and one that characterizes its role as the target. We also present a new loss function that encourages related-product recommendation (RPR) models to select products along outbound graph edges and discourages them from recommending products along inbound edges.
Using MLflow to deploy Graph Neural Networks for Monitoring Supply Chain Risk
We live in an ever interconnected world, and nowhere is this more evident than in modern supply chains. Due to the global macroeconomic environment and globalisation, modern supply chains have become intricately linked and weaved together. Companies worldwide rely on one another to keep their production lines flowing and to act ethically (e.g., complying with laws such as the Modern Slavery Act). From a modelling perspective, the procurement relationships between firms in this global network form an intricate, dynamic, and complex network spanning the globe.
Lastly, it was mentioned earlier that GNNs are a framework for defining deep learning algorithms over graph structured data. For this blog, we will utilise a specific architecture of GNNs called GraphSAGE. This algorithm does not require all nodes to be present during training, is able to generalise to new nodes efficiently, and can scale to billions of nodes. Earlier methods in the literature were transductive, meaning that the algorithms learned embeddings for nodes. This was useful for static graphs, but the algorithms had to be re-run after graph updates such as new nodes. Unlike those methods, GraphSAGE is an inductive framework which learns how to aggregate information from neighborhood nodes; i.e., it learns functions for generating embeddings, rather than learning embeddings directly. Therefore GraphSAGE ensures that we can seamlessly integrate new supply chain relationships retrieved from upstream processes without triggering costly retraining routines.
Improving fault detection and isolation (FDI) in industrial networks using GCNN
Industrial networks of equipment are the backbone of resilient business operations. They are large-scale systems that consist of several interacting components. For example, water supply networks consist of connected components such as water tanks, pumps and pipes. Failure of any one component may disrupt the entire network, making it non-functional, and result in safety hazards and costly repairs. Thus, it is crucial to continuously monitor and maintain industrial networks to prevent any failure. Traditionally, monitoring such systems are focused on detecting faults on the level of a single component by considering the measurements generated by that component. These solutions are sub-optimal as they are independently applied to individual components without explicitly taking into consideration the dependency between the several components that co-exist in the network. Ignoring the interaction between components makes fault detection much more challenging. A fault in a component (say a leakage in a tank or a pipe) can affect the neighboring components. Therefore, designing a monitoring system without considering the network structure can degrade the diagnosis performance significantly. In order to solve this problem, my team and I looked at first modeling the industrial networks as weighted undirected graphs. The graph structure represents the connected components. We then used graph convolutional neural networks (GCNN) to detect and isolate faulty components in these systems. We applied our proposed method to a case study of a simulated water supply network and showed that GCNN outperforms traditional approaches for leakage detection.