Search

Neural combinatorial optimization aims to use neural networks to speed up the solving process of combinatorial optimization problems, i.e., finding the optimal solution of a problem instance from a finite set of feasible solutions that minimize a given objective function. Recently, researchers have applied convolutional neural networks to predict the optimal solution's cost (defined by the objective function) to give as extra input to an exact solver to speed up the solving process. In this paper, we investigate whether graph representations that explicitly model the inherent constraints in combinatorial optimization problems would improve the performance of predicting the optimal solution's cost. Specifically, we use graph neural networks with neighborhood aggregation and graph Transformer models to capture and embed the knowledge in the graph representations of combinatorial optimization problems. We also propose a benchmark dataset containing the Traveling Salesman Problem (TSP) and Job-Shop Scheduling Problem (JSSP), and through the empirical evaluation, we show that graph Transformer models achieve an average loss decrease of 61.05% on TSP and 66.53% on JSSP compared to the baseline convolutional neural networks., QC 20240415Part of ISBN: 79-8-3503-4534-6Partof ISBN:979-8-3503-1891-3

This paper introduces the Hopsworks platform to the entire Earth Observation (EO) data community and the Copernicus programme. Hopsworks is a scalable data-intensive open-source Artificial Intelligence (AI) platform that was jointly developed by Logical Clocks and the KTH Royal Institute of Technology for building end-to-end Machine Learning (ML)/Deep Learning (DL) pipelines for EO data. It provides the full stack of services needed to manage the entire life cycle of data in ML. In particular, Hopsworks supports the development of horizontally scalable DL applications in notebooks and the operation of workflows to support those applications, including parallel data processing, model training, and model deployment at scale. To the best of our knowledge, this is the first work that demonstrates the services and features of the Hopsworks platform, which provide users with the means to build scalable end-to-end ML/DL pipelines for EO data, as well as support for the discovery and search for EO metadata. This paper serves as a demonstration and walkthrough of the stages of building a production-level model that includes data ingestion, data preparation, feature extraction, model training, model serving, and monitoring. To this end, we provide a practical example that demonstrates the aforementioned stages with real-world EO data and includes source code that implements the functionality of the platform. We also perform an experimental evaluation of two frameworks built on top of Hopsworks, namely Maggy and AutoAblation. We show that using Maggy for hyperparameter tuning results in roughly half the wall-clock time required to execute the same number of hyperparameter tuning trials using Spark while providing linear scalability as more workers are added. Furthermore, we demonstrate how AutoAblation facilitates the definition of ablation studies and enables the asynchronous parallel execution of ablation trials., QC 20220506

The property of reversibility is quite meaningful for the classic theoreticabl computer science model, cellular automata. This paper focuses on the reversibility of general one-dimensional (1D) linear cellular automata (LCA), under null boundary conditions over the finite field Zp. Although the existing approaches have split the reversibility challenge into two sub-problems: calculate the period of reversibility first, then verify the reversibility in a period, they are still exponential in the size of the CA's neighborhood. In this paper, we use two efficient algorithms with polynomial complexity to tackle these two challenges, making it possible to solve large-scale reversible LCA, which substantially enlarge its applicability. Finally, we provide an interesting perspective to inversely generate a 1D LCA from a given period of reversibility., QC 20221109

Transformer models have great potential in Graph Representation Learning (GRL) for efficiently scaling the learning process on large datasets and solving many challenges presented in Graph Neural Networks, e.g., oversmoothing and suspended animation. To represent each node of a graph, Transformer models as input usually take a node together with the node context, i.e., a set of other nodes that serve as learning context for the target node. However, current GRL Transformer models mainly consider the graph topology when selecting the node context for each target node. In this work, we demonstrate the important role of node features in selecting the node context. Specifically, we propose a hybrid approach for selecting node context that considers both the graph topology and the semantic similarities between node features. Through the empirical evaluations, we show the advantages of our hybrid node context selection method for a downstream classification task on various datasets compared to selection methods that only consider graph topology or semantic similarities. The best classification accuracy improvements of our proposed hybrid methods over the baseline methods on each dataset range from 0.77% to 6.05%., Part of ISBN 9781665480451QC 20230801

Although selenium (Se) is an essential microelement for humans and animals, it is a potentially toxic element due to its bioaccumulation potential. In this study, Se fertilizer was supplied in a greenhouse vegetable (cucumber) plantation using an innovative system consisting of nanobubbles (NB_Se) and compared to that under conventional conditions of fertigation (C_Se) with six doses. The results revealed that NB_Se significantly reduced soil Se accumulation (38%−144%) and increased cucumber Se content compared with the C_Se treatments at the same Se dose. NB_Se significantly lowered the soil bacterial diversity, with an initial increase and then decrease with the Se doses. Bacterial associations and potential keystone taxa also differed between the NB_Se and C_Se. The greater abundance of oxidizing bacteria (indicated by the function composition of bacterial community) and the improved soil redox environment created by NBs sustained more available Se for plants, leading to a reduction in soil Se residual and an increase in the plant Se content. Our results highlight the feasibility and efficiency of NB_Se and demonstrate the important implications of Se for the maintenance of soil health and sustainability.