Association for Computing Machinery

About: Association for Computing Machinery is a nonprofit organization based out in New York, New York, United States. It is known for research contribution in the topics: Graph (abstract data type) & Context (language use). The organization has 1663 authors who have published 2662 publications receiving 38367 citations. The organization is also known as: ACM & Association of Computing Machinery.

Generalizing Generalizability in Information Systems Research

Abstract: Generalizability is a major concern to those who do, and use, research. Statistical, sampling-based generalizability is well known, but methodologists have long been aware of conceptions of generalizability beyond the statistical. The purpose of this essay is to clarify the concept of generalizability by critically examining its nature, illustrating its use and misuse, and presenting a framework for classifying its different forms. The framework organizes the different forms into four types, which are defined by the distinction between empirical and theoretical kinds of statements. On the one hand, the framework affirms the bounds within which statistical, sampling-based generalizability is legitimate. On the other hand, the framework indicates ways in which researchers in information systems and other fields may properly lay claim to generalizability, and thereby broader relevance, even when their inquiry falls outside the bounds of sampling-based research.

Ward's Hierarchical Clustering Method: Clustering Criterion and Agglomerative Algorithm

Abstract: The Ward error sum of squares hierarchical clustering method has been very widely used since its first description by Ward in a 1963 publication. It has also been generalized in various ways. However there are different interpretations in the literature and there are different implementations of the Ward agglomerative algorithm in commonly used software systems, including differing expressions of the agglomerative criterion. Our survey work and case studies will be useful for all those involved in developing software for data analysis using Ward's hierarchical clustering method.

Dynamic Graph CNN for Learning on Point Clouds

Abstract: Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been proposed in graphics and vision, however, the recent overwhelming success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to the point cloud world. Point clouds inherently lack topological information so designing a model to recover topology can enrich the representation power of point clouds. To this end, we propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv acts on graphs dynamically computed in each layer of the network. It is differentiable and can be plugged into existing architectures. Compared to existing modules operating in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. We show the performance of our model on standard benchmarks including ModelNet40, ShapeNetPart, and S3DIS.

Learning by Collaborating: Convergent Conceptual Change

Abstract: The goal of this article is to construct an integrated approach to collaboration and conceptual change. To this end, a case of conceptual change is analyzed from the point of view of conversational interaction. It is proposed that the crux of collaboration is the problem of convergence: How can two (or more) people construct shared meanings for conversations, concepts, and experiences? Collaboration is analyzed as a process that gradually can lead to convergence of meaning. The epistemological basis of the framework of analysis is a relational, situated view of meaning: Meanings are taken to be relations among situations and verbal or gestural actions. The central claim is that a process described by four primary features can account for students' incremental achievement of convergent conceptual change. The process is characterized by (a) the production of a deep-featured situation, in relation to (b) the interplay of physical metaphors, through the constructive use of (c) interactive cycles of conversati...

Classification of Model Transformation Approaches

Abstract: The Model-Driven Architecture is an initiative by the Object Management Group to automate the generation of platform-specific models from platformindependent models. While there exist some well-established standards for modeling platform models, there is currently no matured foundation for specifying transformations between such models. In this paper, we propose a possible taxonomy for the classification of several existing and proposed model transformation approaches. The taxonomy is described with a feature model that makes the different design choices for model transformations explicit. Based on our analysis, we propose a few major categories in which most model transformation approaches fit.