Aggregation Framework Research Articles

Evaluation of Watershed Development Programme: A Framework for Selection and Aggregation of Key Indicators

The measure of the effectiveness of watershed development programmes depends on selecting the right set of evaluation indicators that reflect the programme’s goals, including resource management, environmental sustainability, and socio-economic benefits. In this paper, the focus is on the process of selecting and aggregating the key indicators to assess the success of watershed development initiatives. By categorizing indicators into relevant themes such as Terrain Management, Water Resources Utilization, Agronomic Vitality, Livestock Vitality, Employability, Human Empowerment, and Sustainability. This paper highlights the importance of using a structured approach to ensure comprehensive evaluation. Proper selection and aggregation of indicators emphasize the importance of context-specific indicators to ensure accurate and effective programme evaluation and lead to providing valuable insights for programme assessment and future improvements.

LGS-PPIS: A Local-Global Structural Information Aggregation Framework for Predicting Protein-Protein Interaction Sites.

Exploring protein-protein interaction sites (PPIS) is of significance to elucidating the intrinsic mechanisms of diverse biological processes. On this basis, recent studies have applied deep learning-based technologies to overcome the high cost of wet experiments for PPIS determination. However, the existing methods still suffer from two limitations that remain to be solved. Firstly, the process of feature aggregation in most methods only took into account node features, but ignored the complex edge features of the target residue to its neighbor residues, resulting in insufficient local feature extraction. Secondly, such feature aggregation was limited to aggregating spatially adjacent residues, and could not capture the "remote" residues that played a critical role in determining PPIS, which can be summed up as the lack of global feature at the residue level. To break the above limitations, a local-global structural information aggregation framework, LGS-PPIS, was proposed in this study, including two modules of edge-aware graph convolutional network (EA-GCN) and self-attention integrated with initial residual and identity mapping (SA-RIM), which achieved the aggregation of local and global information for PPIS prediction. Evaluation results of LGS-PPIS showed that the proposed method outperformed state-of-the-art deep learning methods on three widely used PPIS prediction benchmarks. Besides, the results of ablation experiments demonstrated that the local features from spatially adjacent residues and global features from "remote" residues separately captured by EA-GCN and SA-RIM could benefit the model performance. Among them, the former was shown to have a more significant role in the PPIS prediction.

Analysis on the Influence law and Mechanism of the Strength of Reclaimed Aggregate-Industrial Waste Slag Solidified Silt

To optimize the usage of construction waste resources, industrial waste slag and silt, this paper used Portland cement, mineral waste residue and phosphogypsum composite to make cementing material (CMPS) with construction waste reclaimed aggregate to solidify silt. The laboratory solidification test and microscopic analysis were conducted to assess the mechanical characteristics of solidified sludge. In order to clarify the mineral composition, microscopic morphology and pore characteristics of the regenerated aggregate and CMPS solidified silt (SS), XRD, SEM and nitrogen adsorption pore analyzer were employed for further explore the regenerated aggregate and CMPS solidified silt effectively, and further reveal the internal mechanism of the regenerated aggregate and CMPS solidified silt effectively. The findings indicated that the strength of Portland cementmineral waste residue phosphogypsum terpolymer system curing agent increased by 107.34% than that of single Port-land cement SS at 56 d, and the strength of CMPS solidified silt increased by 25.68% under the action of reclaimed aggregate framework. The maintenance period and water composition of the silt have high correlation with the strength. Therefore, influence law of above two influencing factors on its mechanical properties were further explored and the strength prediction were made. The microscopic test results showed that, drawing from the hydration of Portland cement and pozzolans reaction of mineral waste residue, the solidified system has pre-pared CaSiO3 hydrate gel and ettringite crystals with gelatinous properties, which help to fill the pores and form a denser structure.

Towards value-sensitive and poisoning-proof model aggregation for federated learning on heterogeneous data

Federated Learning (FL) enables collaborative model training without sharing data, but traditional static averaging of local updates leads to poor performance on heterogeneous data. The following remedies, either by scheduling data distribution or mitigating local discrepancies, predominately fail to handle fine-grained heterogeneity (e.g., local imbalanced labels). To commence, we reveal that static averaging leads to the global model suffering from the mean fallacy. That is, the averaging process favors the local model with large parameters numerically rather than knowledge. To tackle this, we introduce FedVSA, a simple-yet-effective model aggregation framework sensitive to heterogeneous local data merits. Specifically, we invent a new global loss function for FL by prioritizing the valuable local updates, facilitating efficient convergence. We deduce a softmax-based aggregation rule and prove its convergence property via rigorous theoretical analysis. Additionally, we expose poisoning threats of model replacement that utilize the mean fallacy for attacks. To mitigate this threat, we propose a two-step mechanism involving auditing historic local training statistics and analyzing the Shapley Value. Through extensive experiments, we show that FedVSA achieves faster convergence (~1.52×) and higher accuracy (~1.6%) compared to the baselines. It also effectively mitigates poisoning attacks by agilely recovering and returning to normal aggregation.

Model-agnostic confidence measurement for aggregating multimodal ensemble models in automatic diagnostic systems

Automatic diagnostic systems (ADSs) have been garnering increased attention because they can alleviate the workload of clinicians by assisting in diagnosis and offering low-cost access to healthcare for people in medically underserved areas. ADS can suggest potential diseases by analyzing a patient's self-report. Previous research on ADS has leveraged diagnostic case data from various patients and medical knowledge to diagnose diseases, with multimodal ensemble methods proving particularly effective. However, the existing multimodal ensemble method combines the probabilities of different models in the aggregating process, which can not properly combine the probabilities that are produced by different criteria. To address these issues, we propose an effective aggregation framework for multimodal ensembles that can properly aggregate model-agnostic confidence scores and predictions from each model. Our framework transforms probability scores from different criteria into unified aggregation rule-based scores and reflects the gap between the probabilities that may be blurred in the aggregation process through the confidence score. In particular, The proposed confidence measurement method employs a post-analysis approach with the developed model or algorithm, making it adaptable in a model-agnostic manner and suitable for multimodal ensemble learning that utilizes heterogeneous prediction results. Our experimental results demonstrate that our framework outperforms existing approaches by more effectively leveraging the strengths of each ensemble member.

A Maneuver in the Trade-Off Space of Federated Learning Aggregation Frameworks Secured with Polymorphic Encryption: PolyFLAM and PolyFLAP Frameworks

Maintaining user privacy in machine learning is a critical concern due to the implications of data collection. Federated learning (FL) has emerged as a promising solution by sharing trained models rather than user data. However, FL still faces several challenges, particularly in terms of security and privacy, such as vulnerability to inference attacks. There is an inherent trade-off between communication traffic across the network and computational costs on the server or client, which this paper aims to address by maneuvering between these performance parameters. To tackle these issues, this paper proposes two complementary frameworks: PolyFLAM (“Polymorphic Federated Learning Aggregation of Models”) and PolyFLAP (“Polymorphic Federated Learning Aggregation of Parameters”). These frameworks provide two options to suit the needs of users, depending on whether they prioritize reducing communication across the network or lowering computational costs on the server or client. PolyFLAM reduces computational costs by exchanging entire models, eliminating the need to rebuild models from parameters. In contrast, PolyFLAP reduces communication costs by transmitting only model parameters, which are smaller in size compared to entire models. Both frameworks are supported by polymorphic encryption, ensuring privacy is maintained even in cases of key leakage. Furthermore, these frameworks offer five different machine learning models, including support vector machines, logistic regression, Gaussian naïve Bayes, stochastic gradient descent, and multi-layer perceptron, to cover as many real-life problems as possible. The evaluation of these frameworks with simulated and real-life datasets demonstrated that they can effectively withstand various attacks, including inference attacks that aim to compromise user privacy by capturing exchanged models or parameters.

Unveiling the Power of Model-Agnostic Multiscale Analysis for Enhancing Artificial Intelligence Models in Breast Cancer Histopathology Images.

Developing AI models for digital pathology has traditionally relied on single-scale analysis of histopathology slides. However, a whole slide image is a rich digital representation of the tissue, captured at various magnification levels. Limiting our analysis to a single scale overlooks critical information, spanning from intricate high-resolution cellular details to broad low-resolution tissue structures. In this study, we propose a model-agnostic multiresolution feature aggregation framework tailored for the analysis of histopathology slides in the context of breast cancer, on a multicohort dataset of 2038 patient samples. We have adapted 9 state-of-the-art multiple instance learning models on our multi-scale methodology and evaluated their performance on grade prediction, TP53 mutation status prediction and survival prediction. The results prove the dominance of the multiresolution methodology, and specifically, concatenating or linearly transforming via a learnable layer the feature vectors of image patches from a high (20x) and low (10x) magnification factors achieve improved performance for all prediction tasks across domain-specific and imagenet-based features. On the contrary, the performance of uniresolution baseline models was not consistent across domain-specific and imagenet-based features. Moreover, we shed light on the inherent inconsistencies observed in models trained on whole-tissue-sections when validated against biopsy-based datasets. Despite these challenges, our findings underscore the superiority of multiresolution analysis over uniresolution methods. Finally, cross-scale analysis also benefits the explainability aspects of attention-based architectures, since one can extract attention maps at the tissue- and cell-levels, improving the interpretation of the model's decision.

Adaptive single-layer aggregation framework for energy-efficient and privacy-preserving load forecasting in heterogeneous Federated smart grids

Federated Learning (FL) enhances predictive accuracy in load forecasting by integrating data from distributed load networks while ensuring data privacy. However, the heterogeneous nature of smart grid load forecasting introduces significant challenges that current methods struggle to address, particularly for resource-constrained devices due to high computational and communication demands. To overcome these challenges, we propose a novel Adaptive Single Layer Aggregation (ASLA) framework tailored for resource-constrained smart grid networks. The ASLA framework mitigates data heterogeneity issues by focusing on local learning and incorporating partial updates from local devices for model aggregation in adaptive manner. It is optimized for resource-constrained environments through the implementation of a stopping criterion during model training and weight quantization. Our evaluation on two distinct datasets demonstrates that quantization results in a minimal loss function degradation of 0.01% for Data 1 and 1.25% for Data 2. Furthermore, local model layer optimization for aggregation achieves substantial communication cost reductions of 829.2-fold for Data 1 and 5,522-fold for Data 2. The use of an 8-bit fixed-point representation for neural network weights leads to a 75% reduction in storage/memory requirements and decreases computational costs by replacing complex floating-point units with simpler fixed-point units. By addressing data heterogeneity and reducing storage, computation, and communication overheads, the ASLA framework is well-suited for deployment in resource-constrained smart grid networks.

CHAI: consensus clustering through similarity matrix integration for cell-type identification.

Several methods have been developed to computationally predict cell-types for single cell RNA sequencing (scRNAseq) data. As methods are developed, a common problem for investigators has been identifying the best method they should apply to their specific use-case. To address this challenge, we present CHAI (consensus Clustering tHrough similArIty matrix integratIon for single cell-type identification), a wisdom of crowds approach for scRNAseq clustering. CHAI presents two competing methods which aggregate the clustering results from seven state-of-the-art clustering methods: CHAI-AvgSim and CHAI-SNF. CHAI-AvgSim and CHAI-SNF demonstrate superior performance across several benchmarking datasets. Furthermore, both CHAI methods outperform the most recent consensus clustering method, SAME-clustering. We demonstrate CHAI's practical use case by identifying a leader tumor cell cluster enriched with CDH3. CHAI provides a platform for multiomic integration, and we demonstrate CHAI-SNF to have improved performance when including spatial transcriptomics data. CHAI overcomes previous limitations by incorporating the most recent and top performing scRNAseq clustering algorithms into the aggregation framework. It is also an intuitive and easily customizable R package where users may add their own clustering methods to the pipeline, or down-select just the ones they want to use for the clustering aggregation. This ensures that as more advanced clustering algorithms are developed, CHAI will remain useful to the community as a generalized framework. CHAI is available as an open source R package on GitHub: https://github.com/lodimk2/chai.

A two-stage image enhancement and dynamic feature aggregation framework for gastroscopy image segmentation

Accurate and reliable automatic segmentation of lesion areas in gastroscopy images can assist endoscopists in making diagnoses and reduce the possibility of missed or incorrect diagnoses. This paper presents a two-stage framework for segmenting gastroscopy images, which aims to improve the accuracy of medical image segmentation tasks using limited datasets. The proposed framework consists of two stages: the Image Enhancement Stage and the Lesion Segmentation Stage. First, in the Image Enhancement Stage, an image enhancement solution called TDC-Enhance is proposed to enrich the original small-scale gastroscopy image dataset. This solution performs Texture Enhancement, Detail Enhancement, and Color Enhancement on the original images. Then, in the Lesion Segmentation Stage, a multi-path automatic segmentation network for gastroscopy images, named DynaSiam, is introduced. DynaSiam comprises a Dependent Encoder, a Shared Encoder, and a Fusion Decoder. It learns feature information related to the lesion region by encoding the different enhanced images obtained in the Image Enhancement Stage as inputs to the multi-path network. Additionally, a Dynamic Feature Interaction (DFI) block is designed to capture and learn deeper image information, thereby improving the segmentation performance of the model. The experimental results show that the proposed method achieves a 90.80% mIoU, 92.71% Dice coefficient and 96.31% Accuracy. Other performance metrics also indicate the best performance, suggesting that the proposed model has significant potential for clinical analysis and diagnosis. Code and implementation details can be found on GitHub: https://github.com/kyasulee/DynaSiam.

The digital trail of Ukraine’s 2022 refugee exodus

When the 2022 Russian full-scale invasion of Ukraine forced millions of people to leave their homes, officials worldwide scrambled to estimate the number of people who would seek refuge in their countries. There were a limited number of official tools in place to lean on to help determine this estimate. In this article, we investigate the possibility of using various publicly available organic (i.e. non-designed) data to predict forced movement from Ukraine early in the crisis. In particular, we establish Ukrainian-language insecurity and contextual indicators from multiple data sources, namely Google Trends, Twitter/X, local newspapers, the ACLED database, and the GDELT database. We compare the usefulness of these indicators in predicting forced migration into three neighboring countries: Poland, Slovakia, and Hungary. To minimize the challenge of temporal misalignment between the organic data and actual movement, we develop a lagging and aggregation framework. Findings reveal Google Trends variables are a robust leading indicator of observed forced migration for this conflict. While other indicators are less strong, they still capture shifts in forced migration flows, highlighting the potential for using publicly available organic data during emerging forced displacement crises.

Decentralized intelligent multi-party competitive aggregation framework for electricity prosumers

Electricity management systems are experiencing significant challenges due to the increased penetration of distributed energy resources. Electricity flows in distribution networks are transforming from unidirectional to bi-directional form. Consumers are transitioning to prosumers with different characteristics, where they take more active roles in electricity generation and consumption. Aggregators are vital financial intermediary agents in the power system transitions, as they could aggregate energy profiles of prosumers. The market competition between aggregators and interactions between prosumers and aggregators are complex and dynamic, which requires a holistic framework to model the market competition. This paper proposes an intelligent aggregation framework with edge computing, enabling decentralized competition for multiple aggregators and prosumers, which can be solved with a graph-based consensus algorithm. This study mathematically proves the proposed algorithm's convergence guarantee and convergence rate. In addition, the proposed framework is applied to an open-source dataset to demonstrate its applicability. Lastly, a benchmark analysis is conducted to show that the proposed algorithm has better communication complexity than the benchmark algorithms.

Linked Exposures Across Databases: an exposure common data elements aggregation framework to facilitate clinical exposure review.

Understanding the health outcomes of military exposures is of critical importance for Veterans, their health care team, and national leaders. Approximately 43% of Veterans report military exposure concerns to their VA providers. Understanding the causal influences of environmental exposures on health is a complex exposure science task and often requires interpreting multiple data sources; particularly when exposure pathways and multi-exposure interactions are ill-defined, as is the case for complex and emerging military service exposures. Thus, there is a need to standardize clinically meaningful exposure metrics from different data sources to guide clinicians and researchers with a consistent model for investigating and communicating exposure risk profiles. The Linked Exposures Across Databases (LEAD) framework provides a unifying model for characterizing exposures from different exposure databases with a focus on providing clinically relevant exposure metrics. Application of LEAD is demonstrated through comparison of different military exposure data sources: Veteran Military Occupational and Environmental Exposure Assessment Tool (VMOAT), Individual Longitudinal Exposure Record (ILER) database, and a military incident report database, the Explosive Ordnance Disposal Information Management System (EODIMS). This cohesive method for evaluating military exposures leverages established information with new sources of data and has the potential to influence how military exposure data is integrated into exposure health care and investigational models.

An ADP framework for flexibility and cost aggregation: Guarantees and open problems

With the increasing amount of Distributed Energy Resources (DERs), coordination of Distribution Grid Operators (DSOs) and Transmission Grid Operators (TSOs) is of paramount importance. Managing a large number of DERs at the TSO level is, however, challenging. To address this problem, flexibility aggregation is a topic of frequent research activities. Aggregation means to describe the combined flexibility of the DERs at the vertical grid coupling between DSO and TSO. Existing works are often limited with respect to guaranteeing feasibility, with respect to efficient numerical implementation, and in terms of quantification of the cost of DER usage. In the present paper, we investigate aggregation based on Approximate Dynamic Programming (ADP). We propose efficient numerical aggregation schemes using tools from computational geometry thus avoiding the need to solve multiple OPF problems. We rely on different variants of the DistFlow model for radial grids, which are computationally efficient. This allows to model of current and voltage limits and enables the consideration of voltage dependencies in the aggregation. Furthermore, we propose a method for cost aggregation and identify open problems of flexibility aggregation.

Multi-agent deep reinforcement learning based fully decentralized aggregation frequency regulation of electric vehicle

Electric vehicles (EVs) are high-quality flexible resources to provide frequency regulation services. However, the EV real-time participation in ancillary service market for frequency regulation (FRASM) under the existing aggregation framework faces data privacy and interest conflicts problems. To solve these issues, this paper proposes the fully-decentralized aggregator (FDA) as a trusted and non-profit agent to replace the traditional aggregator and help EVs interact with FRASM in a decentralized manner. Then a fully decentralized aggregation framework based on consortium blockchain is constructed to protect the interaction data security during frequency regulation process. Furthermore, the inference network is introduced so that EVs can learn better performance and optimize regulation mileage without sharing their private data. This paper proposes an inference network based multi-agent soft actor-critic (IN-MASAC) method that realizes the decentralized interaction between EVs and FRASM and considers multiple user preferences. The case studies demonstrate the efficiency and scalability of the fully decentralized aggregation framework and IN-MASAC method.

Formal Inconsistencies of Expertise Aggregation Techniques Commonly Employed in Engineering Teams

Engineering managers leverage the expertise of engineers in their teams to inform decisions. Engineers may convey their expertise in the form of opinions and/or judgements. Given a decision, it is common to elicit and aggregate the expertise from various engineers to capture a broader set of experiences and knowledge. Establishing an internally and externally consistent aggregation framework is therefore paramount to yield a meaningful aggregation, that is, to make sure that the expertise of each engineer is accounted for reasonably. However, we contend that most de facto aggregation techniques lack such consistency and lead to the inadequate use and aggregation of engineering expertise. In this paper, we investigate the consistency or lack thereof of various expertise aggregation techniques. We derive implications of such inconsistencies and provide recommendations about how they may be overcome. We illustrate our discussion using safety decisions in engineering as a notional case.

Efficient and Secure Aggregation Framework for Federated-Learning-Based Spectrum Sharing

Efficient and Secure Aggregation Framework for Federated-Learning-Based Spectrum Sharing

BMFA-Net: Boundary Constraint Multi-Level Feature Aggregation Framework for Precise Polyp Segmentation

Colorectal cancer is one of the three most common cancers worldwide. Polyps are complex and have unclear boundaries, often leading to inaccurate boundary segmentation and missed detections. To address these challenges, we propose a boundary constraint multi-level feature aggregation framework called BMFA-Net to precisely segment polyps. The framework comprises four key modules. First, the parallel partial decoder is introduced to aggregate high-level features within the network to generate a globally informative semantic map serving as the initial guidance region for reverse erasing the foreground. Second, we propose an efficient atrous convolution attention module to effectively aggregate local and global contextual information over multiple levels. Additionally, a multi-level feature aggregation mechanism is designed and placed among the efficient atrous convolution attention modules to enable the network to capture a large amount of semantic structure while preserving intricate details. Finally, a boundary constraint reverse attention module is proposed to perform the boundary constraint while removing the foreground to improve the quality of boundary segmentation. Extensive experiments demonstrated the superiority and versatility of our framework compared with state-of-the-art methods; specifically, it achieved a mean Dice score of 0.922 on the CVC-300 dataset.

SAF: Smart Aggregation Framework for Revealing Atoms Importance Rank and Improving Prediction Rates in Drug Discovery.

Machine learning, and representation learning in particular, has the potential to facilitate drug discovery by screening a large chemical space in silico. A successful approach for representing molecules is to treat them as graphs and utilize graph neural networks. One of the key limitations of such methods is the necessity to represent compounds with different numbers of atoms, which requires aggregating the atom's information. Common aggregation operators, such as averaging, result in a loss of information at the atom level. In this work, we propose a novel aggregating approach where each atom is weighted nonlinearly using the Boltzmann distribution with a hyperparameter analogous to temperature. We show that using this weighted aggregation improves the ability of the gold standard message-passing neural network to predict antibiotic activity. Moreover, by changing the temperature hyperparameter, our approach can reveal the atoms that are important for activity prediction in a smooth and consistent way, thus providing a novel regulated attention mechanism for graph neural networks. We further validate our method by showing that it recapitulates the functional group in β-lactam antibiotics. The ability of our approach to rank the atoms' importance for a desired function can be used within any graph neural network to provide interpretability of the results and predictions at the node level.

Optimal demand response aggregation in wholesale electricity markets: Comparative analysis of polyhedral; ellipsoidal and box methods for modeling uncertainties

This paper presents an optimal framework for demand response aggregators in wholesale electricity markets. Demand response aggregators provide customers with flexible contracts in the proposed model. These contracts allow for hourly load reductions through load curtailment, load shifting, onsite generation utilization, and energy storage systems. The study suggests the price-based self-scheduling model for demand response aggregators, which seeks to maximize the aggregator's payoff for participation in day-ahead energy markets. The proposed model is implemented on a sample demand response aggregator with uncertainty and without uncertainty. Three methods, box, polyhedral, and ellipsoidal, based on robust optimization, are proposed for uncertainty modeling in this work, and their effectiveness is compared with each other. The results show that if the uncertainty is modeled using the polyhedral method, the value of the objective function will deviate by only 22.72 % compared to the case without uncertainty. However, this deviation in box and ellipsoidal methods is 118.48 % and 49.20 %, respectively, which shows the superiority of the polyhedral method compared to the oval and box methods.