Publication | International Conference on Machine Learning and Applications 2022
SimCURL
Simple Contrastive User Representation Learning from Command Sequences
SimCURL learns user representations from a large corpus of unlabeled command sequences. These learned representations are then transferred to multiple downstream tasks that have only limited labels available.
This paper is an effort towards user modeling based on the raw command sequences of Fusion360. Proper encoding of commands are crucial for better understanding user behavior and making intelligent software. In SimCURL we proposed a method for learning representations of these command sequences.
Download publicationAbstract
SimCURL: Simple Contrastive User Representation Learning from Command Sequences
Hang Chu, Amir Khasahmadi, Karl D.D. Willis, Fraser Anderson, Yaoli Mao, Linh Tran, Justin Matejka, Jo Vermeulen
International Conference on Machine Learning and Applications 2022
User modeling is crucial to understanding user behavior and essential for improving user experience and personalized recommendations. When users interact with software, vast amounts of command sequences are generated through logging and analytics systems. These command sequences contain clues to the users’ goals and intents. However, these data modalities are highly unstructured and unlabeled, making it difficult for standard predictive systems to learn from. We propose SimCURL, a simple yet effective contrastive self-supervised deep learning framework that learns user representation from unlabeled command sequences. Our method introduces a user-session network architecture, as well as session dropout as a novel way of data augmentation. We train and evaluate our method on a real-world command sequence dataset of more than half a billion commands. Our method shows significant improvement over existing methods when the learned representation is transferred to downstream tasks such as experience and expertise classification.
Related Resources
2024
Exploring Opportunities for Adopting Generative AI in Automotive Conceptual DesignThis research discusses opportunities for adopting generative AI in…
2023
A Hybrid Intelligence Approach to Training Generative Design Assistants: Partnership Between Human Experts and AI Enhanced Co-Creative ToolsThe research presents a framework for designing and evaluating…
2023
Extracting Design Knowledge from Optimization Data: Enhancing Engineering Design in Fluid Based Thermal Management SystemsExtracting knowledge from optimization data in multi-split thermal…
2021
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design SequencesParametric computer-aided design (CAD) is a standard paradigm used to…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us