A Framework for Developing Diagram Applications

2014 ◽  
pp. 339-348
Author(s):  
Wei Lai ◽  
Weidong Huang
Keyword(s):  
Case Studies ◽  
Real World ◽  
Graph Structure ◽  
Real World Applications ◽  
Automatic Layout ◽  
Uml Diagrams ◽  
Application Specific ◽  
Shape And Size

This chapter presents a framework for developing diagram applications. The diagrams refer to those graphs where nodes vary in shape and size used in real world applications, such as flowcharts, UML diagrams, and E-R diagrams. The framework is based on a model the authors developed for diagrams. The model is robust for diagrams and it can represent a wide variety of applications and support the development of powerful application-specific functions. The framework based on this model supports the development of automatic layout techniques for diagrams and the development of the linkage between the graph structure and applications. Automatic layout for diagrams is demonstrated and two case studies for diagram applications are presented.

Efficient inference for agent-based models of real-world phenomena

2021 ◽  
Author(s):  
Andreas Christ Sølvsten Jørgensen ◽  
Atiyo Ghosh ◽  
Marc Sturrock ◽  
Vahid Shahrezaei
Keyword(s):  
Machine Learning ◽  
Case Studies ◽  
Parameter Space ◽  
Real World ◽  
Autonomous Agents ◽  
Stochastic Simulations ◽  
Model Parameters ◽  
Learning Approaches ◽  
Real World Applications ◽  
Real World Problems

AbstractThe modelling of many real-world problems relies on computationally heavy simulations. Since statistical inference rests on repeated simulations to sample the parameter space, the high computational expense of these simulations can become a stumbling block. In this paper, we compare two ways to mitigate this issue based on machine learning methods. One approach is to construct lightweight surrogate models to substitute the simulations used in inference. Alternatively, one might altogether circumnavigate the need for Bayesian sampling schemes and directly estimate the posterior distribution. We focus on stochastic simulations that track autonomous agents and present two case studies of real-world applications: tumour growths and the spread of infectious diseases. We demonstrate that good accuracy in inference can be achieved with a relatively small number of simulations, making our machine learning approaches orders of magnitude faster than classical simulation-based methods that rely on sampling the parameter space. However, we find that while some methods generally produce more robust results than others, no algorithm offers a one-size-fits-all solution when attempting to infer model parameters from observations. Instead, one must choose the inference technique with the specific real-world application in mind. The stochastic nature of the considered real-world phenomena poses an additional challenge that can become insurmountable for some approaches. Overall, we find machine learning approaches that create direct inference machines to be promising for real-world applications. We present our findings as general guidelines for modelling practitioners.Author summaryComputer simulations play a vital role in modern science as they are commonly used to compare theory with observations. One can thus infer the properties of a observed system by comparing the data to the predicted behaviour in different scenarios. Each of these scenarios corresponds to a simulation with slightly different settings. However, since real-world problems are highly complex, the simulations often require extensive computational resources, making direct comparisons with data challenging, if not insurmountable. It is, therefore, necessary to resort to inference methods that mitigate this issue, but it is not clear-cut what path to choose for any specific research problem. In this paper, we provide general guidelines for how to make this choice. We do so by studying examples from oncology and epidemiology and by taking advantage of developments in machine learning. More specifically, we focus on simulations that track the behaviour of autonomous agents, such as single cells or individuals. We show that the best way forward is problem-dependent and highlight the methods that yield the most robust results across the different case studies. We demonstrate that these methods are highly promising and produce reliable results in a small fraction of the time required by classic approaches that rely on comparisons between data and individual simulations. Rather than relying on a single inference technique, we recommend employing several methods and selecting the most reliable based on predetermined criteria.

Chapter 15. Human-Centered Concept Explanations for Neural Networks

2021 ◽  
Author(s):  
Chih-Kuan Yeh ◽  
Been Kim ◽  
Pradeep Ravikumar
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Case Studies ◽  
Real World ◽  
Deep Neural Networks ◽  
Learning Models ◽  
Real World Applications ◽  
The Right ◽  
Concept Activation ◽  
Machine Learning Models

Understanding complex machine learning models such as deep neural networks with explanations is crucial in various applications. Many explanations stem from the model perspective, and may not necessarily effectively communicate why the model is making its predictions at the right level of abstraction. For example, providing importance weights to individual pixels in an image can only express which parts of that particular image is important to the model, but humans may prefer an explanation which explains the prediction by concept-based thinking. In this work, we review the emerging area of concept based explanations. We start by introducing concept explanations including the class of Concept Activation Vectors (CAV) which characterize concepts using vectors in appropriate spaces of neural activations, and discuss different properties of useful concepts, and approaches to measure the usefulness of concept vectors. We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats. Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.

scholarly journals Semi-supervised User Profiling with Heterogeneous Graph Attention Networks

2019 ◽  
Author(s):  
Weijian Chen ◽  
Yulong Gu ◽  
Zhaochun Ren ◽  
Xiangnan He ◽  
Hongtao Xie ◽  
...  
Keyword(s):  
Social Networks ◽  
Real World ◽  
User Profiling ◽  
Graph Structure ◽  
User Characteristics ◽  
Attention Networks ◽  
User Behaviors ◽  
Real World Applications ◽  
Purchase Behaviors ◽  
Personal Interests

Aiming to represent user characteristics and personal interests, the task of user profiling is playing an increasingly important role for many real-world applications, e.g., e-commerce and social networks platforms. By exploiting the data like texts and user behaviors, most existing solutions address user profiling as a classification task, where each user is formulated as an individual data instance. Nevertheless, a user's profile is not only reflected from her/his affiliated data, but also can be inferred from other users, e.g., the users that have similar co-purchase behaviors in e-commerce, the friends in social networks, etc. In this paper, we approach user profiling in a semi-supervised manner, developing a generic solution based on heterogeneous graph learning. On the graph, nodes represent the entities of interest (e.g., users, items, attributes of items, etc.), and edges represent the interactions between entities. Our heterogeneous graph attention networks (HGAT) method learns the representation for each entity by accounting for the graph structure, and exploits the attention mechanism to discriminate the importance of each neighbor entity. Through such a learning scheme, HGAT can leverage both unsupervised information and limited labels of users to build the predictor. Extensive experiments on a real-world e-commerce dataset verify the effectiveness and rationality of our HGAT for user profiling.

The Economics of Platforms

2021 ◽  
Author(s):  
Paul Belleflamme ◽  
Martin Peitz
Keyword(s):  
Case Studies ◽  
Real World ◽  
Network Effects ◽  
Driving Forces ◽  
Digital Platforms ◽  
Vital Importance ◽  
Everyday Lives ◽  
Key Concepts ◽  
Real World Applications ◽  
Price Strategies

Digital platforms controlled by Alibaba, Alphabet, Amazon, Facebook, Netflix, Tencent and Uber have transformed not only the ways we do business, but also the very nature of people's everyday lives. It is of vital importance that we understand the economic principles governing how these platforms operate. This book explains the driving forces behind any platform business with a focus on network effects. The authors use short case studies and real-world applications to explain key concepts such as how platforms manage network effects and which price and non-price strategies they choose. This self-contained text is the first to offer a systematic and formalized account of what platforms are and how they operate, concisely incorporating path-breaking insights in economics over the last twenty years.

scholarly journals GraphPrompt: Biomedical Entity Normalization Using Graph-based Prompt Templates

2021 ◽  
Author(s):  
Jiayou Zhang ◽  
Zhirui Wang ◽  
Shizhuo Zhang ◽  
Megh Manoj Bhalerao ◽  
Yucong Liu ◽  
...  
Keyword(s):  
Real World ◽  
Life Sciences ◽  
Cell Types ◽  
Learning Approach ◽  
Biomedical Data ◽  
Graph Structure ◽  
Holistic View ◽  
Real World Applications ◽  
Different Types ◽  
Unique Graph

Biomedical entity normalization unifies the language across biomedical experiments and studies, and further enables us to obtain a holistic view of life sciences. Current approaches mainly study the normalization of more standardized entities such as diseases and drugs, while disregarding the more ambiguous but crucial entities such as pathways, functions and cell types, hindering their real-world applications. To achieve biomedical entity normalization on these under-explored entities, we first introduce an expert-curated dataset OBO-syn encompassing 70 different types of entities and 2 million curated entity-synonym pairs. To utilize the unique graph structure in this dataset, we propose GraphPrompt, a prompt-based learning approach that creates prompt templates according to the graphs. GraphPrompt obtained 41.0% and 29.9% improvement on zero-shot and few-shot settings respectively, indicating the effectiveness of these graph-based prompt templates. We envision that our method GraphPrompt and OBO-syn dataset can be broadly applied to graph-based NLP tasks, and serve as the basis for analyzing diverse and accumulating biomedical data.

Sign in / Sign up

Export Citation Format

Share Document