Ranjitha Kumar
Ranjitha Kumar
I'm the Chief Scientist at Apropose, Inc., a Bay Area startup I co-founded to build data-driven design software for the Web.

In the Fall of 2014, I'll be joining the Department of Computer Science at the University of Illinois at Urbana-Champaign as an Assistant Professor.

I received my PhD from the Department of Computer Science at Stanford University, where I worked with Scott Klemmer.

FTM Thumbnail
Design Mining the Web
Ranjitha Kumar
Ph.D. Dissertation, Stanford University Computer Science Department
 ·  www ·  video
The billions of pages on the Web today provide an opportunity to understand design practice on a massive scale. Each page comprises a concrete example of visual problem solving, creativity, and aesthetics. In recent years, data mining and knowledge discovery have revolutionized the Web, driving search engines, advertising platforms, and recommender systems that are used by more than two billion people every day. However, traditional data mining techniques tend to focus on the content of Web pages, ignoring how that content is presented. What could we learn from mining design? This thesis introduces design mining for the Web, and presents a scalable software platform for Web design mining called Webzeitgeist. Webzeitgeist consists of a repository of pages processed into data structures that facilitate large-scale design knowledge extraction. With Webzeitgeist, users can find, understand, and leverage visual design data in Web applications. In this dissertation, I demonstrate how software tools built on top of Webzeitgeist can be used to dynamically curate design galleries, search for design alternatives, retarget content between page designs, and even predict the semantic role of page elements from design data. As more and more creative work is done digitally and shared in the cloud, Webzeitgeist illustrates how design mining principles can be applied to benefit content creators and consumers.
FTM Thumbnail
Webzeitgeist: Design Mining the Web
Ranjitha Kumar, Arvind Satyanarayan, Cesar Torres, Maxine Lim, Salman Ahmad, Scott R. Klemmer, and Jerry O. Talton
Proceedings of CHI '13
 ·  slides ·  video ·  best paper award
Advances in data mining and knowledge discovery have transformed the way Web sites are designed. However, while visual presentation is an intrinsic part of the Web, traditional data mining techniques ignore render-time page structures and their attributes. This paper introduces design mining for the Web: using knowledge discovery techniques to understand design demographics, automate design curation, and support data-driven design tools. This idea is manifest in Webzeitgeist, a platform for large-scale design mining comprising a repository of over 100,000 Web pages and 100 million design elements. This paper describes the principles driving design mining, the implementation of the Webzeitgeist architecture, and the new class of data-driven design applications it enables.
structural semantics overview 
Learning Structural Semantics for the Web
Maxine Lim, Ranjitha Kumar, Arvind Satyanarayan, Cesar Torres, Jerry O. Talton, and Scott R. Klemmer
Stanford University CSTR 2012-03
Researchers have long envisioned a Semantic Web, where unstructured Web content is replaced by documents with rich semantic annotations. Unfortunately, this vision has been hampered by the difficulty of acquiring semantic metadata for Web pages. This paper introduces a method for automatically "semantifying" structural page elements: using machine learning to train classifiers that can be applied in a post-hoc fashion. We focus on one popular class of semantic identifiers: those concerned with the structure―or information architecture―of a page. To determine the set of structural semantics to learn and to collect training data for the learning, we gather a large corpus of labeled page elements from a set of online workers. We discuss the results from this collection and demonstrate that our classifiers learn structural semantics in a general way.
FTM Thumbnail
Learning Design Patterns with Bayesian Grammar Induction
Jerry O. Talton, Lingfeng Yang, Ranjitha Kumar, Maxine Lim, Noah D. Goodman, and Radomír Měch
Proceedings of UIST '12
 ·  slides ·  best paper nominee
Design patterns have proven useful in many creative fields, providing content creators with archetypal, reusable guidelines to leverage in projects. Creating such patterns, however, is a time-consuming, manual process, typically relegated to a few experts in any given domain. In this paper, we describe an algorithmic method for learning design patterns directly from data using techniques from natural language processing and structured concept learning. Given a set of labeled, hierarchical designs as input, we induce a probabilistic formal grammar over these exemplars. Once learned, this grammar encodes a set of generative rules for the class of designs, which can be sampled to synthesize novel artifacts. We demonstrate the method on geometric models and Web pages, and discuss how the learned patterns can drive new interaction mechanisms for content creators.
UIST Poster '12 Thumbnail
Data-Driven Interactions for Web Design
extended abstract ·  slides
Ranjitha Kumar
Doctoral Symposium, UIST '12
This thesis describes how data-driven approaches to Web design problems can enable useful interactions for designers. It presents three machine learning applications which enable new interaction mechanisms for Web design: rapid retargeting between page designs, scalable design search, and gener- ative probabilistic model induction to support design interactions cast as probabilistic inference. It also presents a scalable architecture for efficient data-mining on Web designs, which supports these three applications.
FTM Thumbnail
Data-Driven Web Design
Ranjitha Kumar, Jerry O. Talton, Salman Ahmad, and Scott R. Klemmer
Proceedings of ICML '12
 ·  slides ·  invited applications paper
This short paper summarizes challenges and opportunities of applying machine learning methods to Web design problems, and describes how structured prediction, deep learning, and probabilistic program induction can enable useful interactions for designers. We intend for these techniques to foster new work in data-driven Web design.
FTM Thumbnail
Flexible Tree Matching
Ranjitha Kumar, Jerry O. Talton, Salman Ahmad, Tim Roughgarden, and Scott R. Klemmer
Proceedings of IJCAI '11
 ·  invited paper
Tree-matching problems arise in many computational domains. The literature provides several methods for creating correspondences between labeled trees; however, by definition, tree-matching algorithms rigidly preserve ancestry. That is, once two nodes have been placed in correspondence, their descendants must be matched as well. We introduce flexible tree matching, which relaxes this rigid requirement in favor of a tunable formulation in which the role of hierarchy can be controlled. We show that flexible tree matching is strongly NP-complete, give a stochastic approximation algorithm for the problem, and demonstrate how structured prediction techniques can learn the algorithm's parameters from a set of example matchings. Finally, we present results from applying the method to tasks in Web design.
Bricolage Thumbnail
Bricolage: Example-Based Retargeting for Web Design
Ranjitha Kumar, Jerry O. Talton, Salman Ahmad, and Scott R. Klemmer
Proceedings of CHI '11
 ·  slides ·  www ·  best paper award
The Web provides a corpus of design examples unparalleled in human history. However, leveraging existing designs to produce new pages is often difficult. This paper introduces the Bricolage algorithm for transferring design and content between Web pages. Bricolage employs a novel, structured-prediction technique that learns to create coherent mappings between pages by training on human-generated exemplars. The produced mappings are then used to automatically transfer the content from one page into the style and layout of another. We show that Bricolage can learn to accurately reproduce human page mappings, and that it provides a general, efficient, and automatic technique for retargeting content between a variety of real Web pages.
Adaptive Ideas Thumbnail
Designing with Interactive Example Galleries
Brian Lee, Savil Srivastava, Ranjitha Kumar, Ronen Brafman, and Scott R Klemmer
Proceedings of CHI '10
Designers often use examples for inspiration; examples offer contextualized instances of how form and content integrate. Can interactive example galleries bring this practice to everyday users doing design work, and does working with examples help the designs they create? This paper explores whether people can realize significant value from explicit mechanisms for designing by example modification. We present the results of three studies, finding that independent raters prefer designs created with the aid of examples, that users prefer adaptively selected examples to random ones, and that users make use of multiple examples when creating new designs. To enable these studies and demonstrate how software tools can facilitate designing with examples, we introduce interface techniques for browsing and borrowing from a corpus of examples, manifest in the Adaptive Ideas Web design tool. Adaptive Ideas leverages a faceted metadata interface for viewing and navigating example galleries.
UIST Poster '09 Thumbnail
Crowdsourcing Interface for Collecting Correspondences Between Web Pages
Juho Kim, Ranjitha Kumar, and Scott R Klemmer
Poster, Adjunct Proceedings of UIST '09
One challenge in building a web design tool that attempts to leverage examples is gathering design alternatives and providing mappings between web page elements. We present a crowdsourcing interface to collect user-generated correspondences between two web pages. Our iterative refinement of the interface was guided by three main design principles: modularize the task, minimize user errors, and provide relevant information. As an initial experiment, we collected fifteen web pages with diverse style and layout, and deployed the interface on Amazon’s Mechanical Turk. Preliminary data analysis shows that Turkers take longer than experts and define fewer mappings in general. Further evaluation and experiments with different types of pages will identify directions for a web design tool that enables the use of any web page as a design template.
CHI Poster '09 Thumbnail
Automatic Retargeting of Web Page Content
Ranjitha Kumar, Juho Kim, and Scott R Klemmer
Poster, Extended Abstracts of CHI '09
We present a novel technique for automatically retargeting content from one web page onto the layout of another. Web pages are decomposed into their perceptual hierarchical representations. We then use a structured-prediction algorithm to learn reasonable mappings between the perceptual trees. Using the mappings, we are able to merge the content of one page with the layout of another.
skeleton muscle front  skeleton muscle back
Volume Preserving Sinusoidal Muscles for Surface Skinning
Ranjitha Kumar
Senior Honors Thesis, Stanford University '07
This thesis presents a volume-preserving analytic muscle model that can be embedded within a skin mesh to induce realistic, physics-based deformation during simulation. These volumetric muscles are layered on top of a dynamic framework of linear, segment-based muscles that drive the underlying skeletal structure. The result is an integrated system that supports realistic skin deformation along a specified target motion while requiring only minimal computational resources.
honors and awards
ACM CHI Best Paper Award (2013)
ACM UIST Best Paper Nominee (2012)
Google PhD Fellowship (2011)
ACM CHI Best Paper Award (2011)
NSF Graduate Research Fellowship Competition, Honorable Mention (2007, 2008)
Stanford University School of Engineering Fellowship (2007)
Computer Research Association Outstanding Undergraduate, Honorable Mention (2007)
Course Assistant, Stanford University (Fall 2008)
CS147: Introduction to HCI Design
Stanford Teaching Fellow, Stanford University (Summer 2008)
CS148: Introductory Computer Graphics
Course Assistant, Stanford University (Summer 2007)
CS148: Introductory Computer Graphics
Instructor, Stanford University (Fall 2006)
CS1C: Introduction to Computing at Stanford