Justin Chen

Matthew Hull, Connor Guerin, Justin Chen et al.

Manually grading D3 data visualizations is a challenging endeavor, and is especially difficult for large classes with hundreds of students. Grading an interactive visualization requires a combination of interactive, quantitative, and qualitative evaluation that are conventionally done manually and are difficult to scale up as the visualization complexity, data size, and number of students increase. We present a first-of-its kind automatic grading method for D3 visualizations that scalably and precisely evaluates the data bindings, visual encodings, interactions, and design specifications used in a visualization. Our method has shown potential to enhance students' learning experience, enabling them to submit their code frequently and receive rapid feedback to better inform iteration and improvement to their code and visualization design. Our method promotes consistent grading and enables instructors to dedicate more focus to assist students in gaining visualization knowledge and experience. We have successfully deployed our method and auto-graded D3 submissions from more than 1000 undergraduate and graduate students in Georgia Tech's CSE6242 Data and Visual Analytics course, and received positive feedback and encouragement for expanding its adoption.

Justin Chen, Christopher Eur, Greg Yang et al.

Function classes are collections of Boolean functions on a finite set, which are fundamental objects of study in theoretical computer science. We study algebraic properties of ideals associated to function classes previously defined by the third author. We consider the broad family of intersection-closed function classes, and describe cellular free resolutions of their ideals by order complexes of the associated posets. For function classes arising from matroids, polyhedral cell complexes, and more generally interval Cohen-Macaulay posets, we show that the multigraded Betti numbers are pure, and are given combinatorially by the Möbius functions. We then apply our methods to derive bounds on the VC dimension of some important families of function classes in learning theory.

Justin Chen, Edward Gan, Kexin Rong et al.

Domain adaptation provides a powerful set of model training techniques given domain-specific training data and supplemental data with unknown relevance. The techniques are useful when users need to develop models with data from varying sources, of varying quality, or from different time ranges. We build CrossTrainer, a system for practical domain adaptation. CrossTrainer utilizes loss reweighting, which provides consistently high model accuracy across a variety of datasets in our empirical analysis. However, loss reweighting is sensitive to the choice of a weight hyperparameter that is expensive to tune. We develop optimizations leveraging unique properties of loss reweighting that allow CrossTrainer to output accurate models while improving training time compared to naive hyperparameter search.

Justin Chen

In the neuroevolution literature, research has primarily focused on evolving the number of nodes, connections, and weights in artificial neural networks. Few attempts have been made to evolve activation functions. Research in evolving activation functions has mainly focused on evolving function parameters, and developing heterogeneous networks by selecting from a fixed pool of activation functions. This paper introduces a novel technique for evolving heterogeneous artificial neural networks through combinatorially generating piecewise activation functions to enhance expressive power. I demonstrate this technique on NeuroEvolution of Augmenting Topologies using ArcTan and Sigmoid, and show that it outperforms the original algorithm on non-Markovian double pole balancing. This technique expands the landscape of unconventional activation functions by demonstrating that they are competitive with canonical choices, and introduces a purview for further exploration of automatic model selection for artificial neural networks.