Abstract Stream processing requires integrating with background knowledge in order to become rich knowledge. As a promising approach, it is getting important to combine streaming data with linked open data. However, since linked data change dynamically, it is impossible to synchronize their distributed data sources perfectly and seamlessly. To reduce the high cost of the synchronization, the materialized views (or views) that store local copies of remote sources are used but may degrade the accuracy of stream processing. To balance response time against accuracy, recent works manage a refresh budget—that is, the limited cost allocated for updating views over remote sources. However, they fail to allocate a refresh budget and produce a low accuracy when a tight deadline is given. To solve the problem, we propose an efficient method of allocating a refresh budget to view updates. The proposed method updates views both in the background and on demand. Experimental results with real and synthetic data sets show that the proposed method achieves superiority in terms of answer staleness, resource utilization, and refresh budget usage.

Cold items are a critical problem in the recommendation domain because newly introduced items lack user–item interactions to train accurate collaborative filters (CFs). Recent studies have adopted neural networks such as MLPs and autoencoders to predict collaborative embeddings learned by CFs, using items’ side information available at the time of registration. As a generative model, diffusion models have achieved success in various fields, such as image generation and natural language processing, through their superior generative capability. This paper proposes a diffusion model as a base for cold item recommendation by generating collaborative embeddings for cold items. First, using a diffusion model with our customized predictor, we directly generate items’ collaborative embeddings conditioned on their side information. Then, a second-stage refiner, which adopts simple MLPs and dropout, is trained to calculate the final recommendation scores. The proposed method requires only the user embeddings from the existing model and the side information of cold items, making it easy to integrate into existing recommender systems. Extensive experiments on real-world datasets show that the proposed method outperforms state-of-the-art baseline methods and indicates the potential of diffusion models in cold item recommendation.

Abstract Stream processing requires integrating with background knowledge in order to become rich knowledge. As a promising approach, it is getting important to combine streaming data with linked open data. However, since linked data change dynamically, it is impossible to synchronize their distributed data sources perfectly and seamlessly. To reduce the high cost of the synchronization, the materialized views (or views) that store local copies of remote sources are used but may degrade the accuracy of stream processing. To balance response time against accuracy, recent works manage a refresh budget—that is, the limited cost allocated for updating views over remote sources. However, they fail to allocate a refresh budget and produce a low accuracy when a tight deadline is given. To solve the problem, we propose an efficient method of allocating a refresh budget to view updates. The proposed method updates views both in the background and on demand. Experimental results with real and synthetic data sets show that the proposed method achieves superiority in terms of answer staleness, resource utilization, and refresh budget usage.

Cold items are a critical problem in the recommendation domain because newly introduced items lack user–item interactions to train accurate collaborative filters (CFs). Recent studies have adopted neural networks such as MLPs and autoencoders to predict collaborative embeddings learned by CFs, using items’ side information available at the time of registration. As a generative model, diffusion models have achieved success in various fields, such as image generation and natural language processing, through their superior generative capability. This paper proposes a diffusion model as a base for cold item recommendation by generating collaborative embeddings for cold items. First, using a diffusion model with our customized predictor, we directly generate items’ collaborative embeddings conditioned on their side information. Then, a second-stage refiner, which adopts simple MLPs and dropout, is trained to calculate the final recommendation scores. The proposed method requires only the user embeddings from the existing model and the side information of cold items, making it easy to integrate into existing recommender systems. Extensive experiments on real-world datasets show that the proposed method outperforms state-of-the-art baseline methods and indicates the potential of diffusion models in cold item recommendation.

Identifying key factors and analyzing their causal relationships significantly enhance decision-making effectiveness in site selection. Although numerous studies have applied Multi-Criteria Decision-Making (MCDM) methods to site selection, these traditional approaches often overlook or inadequately represent causal interdependencies among factors. This study addresses these limitations by utilizing open data for transparency and employing Bayesian Networks (BN) as a robust probabilistic modeling alternative. BNs effectively represent complex factor interactions, capturing both causal relationships and uncertainties. Experimental evaluations demonstrate that the proposed framework effectively calculates final site suitability probabilities by explicitly considering hierarchical dependencies, offering enhanced decision-making insights.

Distributed renewable energy resources (DERs) like solar and wind have become key sustainable energy sources. However, their small scale and variability challenge stable energy supply, and thus DERs should be managed collectively as virtual energy plants (VPPs). Existing energy prediction uncertainties reduce trust in VPPs, limiting market growth. To address this, we propose a trust-aware prediction adjustment method. By defining DER reliability as a quantitative metric, our approach improves prediction accuracy. Experiments on real-world data show the method outperforms existing techniques in reducing non-trust hit rates.

The Digital Twin Government (DTG) paradigm seeks to digitally replicate vast and heterogeneous governmental resources for decision-making and service delivery in real-world scenarios. In this paper, we introduce a Semantic Table Augmentation (STA) framework that automates the semantic enrichment of diverse tabular data using Large Language Models (LLMs). First, we propose the Digital Civil Complaint Ontology (DCCO) that expresses entities and their relationships in civil complaint management under DTG contexts. Our context-driven prompt templates enable the deployment of LLMs in a model-agnostic manner. Finally, we evaluate the performance of our proposed methods on synthetic datasets using cutting-edge LLMs against state-of-the-art method.

Recently, many deep learning models have been trained in geographically distributed data centers. The carbon emissions produced by training the models may pose a significant threat to climate change like increasing temperatures. Existing studies have a hardship in shifting the workload of training models to a data center with low carbon emissions. So, they fail to ensure low emissions of the workload during training, especially when long-term workloads like Large Language Models (LLMs) are trained. To cope with this problem, we propose a method that shifts the workload to a cloud with low carbon emissions while enduring a lack of computational resources. Specifically, we define a task scheduler that includes states and their transitions to migrate mini-batches dynamically. Next, we present a fault-tolerant control that optimizes a GPU frequency to adapt to workload variations of training models while guaranteeing its power consumption. Last, we conducted exhaustive experiments using real-world data in terms of carbon emissions, transfer time, and power consumption compared to state-of-the-art methods.