More Like this

1. The Impacts of Referent Display on Gesture and Speech Elicitation

   https://doi.org/10.1109/TVCG.2022.3203090  

   Williams, Adam S.; Ortega, Francisco R. (July 2022, IEEE Transactions on Visualization and Computer Graphics)

   Elicitation studies have become a popular method of participatory design. While traditionally used to examine unimodal gesture interactions, elicitation has started being used with other novel interaction modalities. Unfortunately, there has been no work that examines the impact of referent display on elicited interaction proposals. To address that concern this work provides a detailed comparison between two elicitation studies that were similar in design apart from the way that participants were prompted for interaction proposals (i.e., the referents). Based on this comparison the impact of referent display on speech and gesture interaction proposals are each discussed. The interaction proposals between these elicitation studies were not identical. Gesture proposals were the least impacted by referent display, showing high proposal similarity between the two works. Speech proposals were highly biased by text referents with proposals directly mirroring text-based referents an average of 69.36% of the time. In short, the way that referents are presented during elicitation studies can impact the resulting interaction proposals; however, the level of impact found is dependent on the modality of input elicited. 

   more » « less
2. The Cost of Production in Elicitation Studies and the Legacy Bias-Consensus Trade off

   https://doi.org/10.3390/mti4040088  

   Williams, Adam S.; Garcia, Jason; De Zayas, Fernando; Hernandez, Fidel; Sharp, Julia; Ortega, Francisco R. (December 2020, Multimodal Technologies and Interaction)

   null (Ed.)

   Gesture elicitation studies are a popular means of gaining valuable insights into how users interact with novel input devices. One of the problems elicitation faces is that of legacy bias, when elicited interactions are biased by prior technologies use. In response, methodologies have been introduced to reduce legacy bias. This is the first study that formally examines the production method of reducing legacy bias (i.e., repeated proposals for a single referent). This is done through a between-subject study that had 27 participants per group (control and production) with 17 referents placed in a virtual environment using a head-mounted display. This study found that over a range of referents, legacy bias was not significantly reduced over production trials. Instead, production reduced participant consensus on proposals. However, in the set of referents that elicited the most legacy biased proposals, production was an effective means of reducing legacy bias, with an overall reduction of 11.93% for the chance of eliciting a legacy bias proposal. 

   more » « less
3. Quadratic metric elicitation for fairness and beyond

   Hiranandani, Gaurush; Mathur, Jatin; Narasimhan, Harikrishna; Koyejo, Oluwasanmi (January 2022, Proceedings of Machine Learning Research)

   Cussens, James; Zhang, Kun (Ed.)

   Metric elicitation is a recent framework for eliciting classification performance metrics that best reflect implicit user preferences based on the task and context. However, available elicitation strategies have been limited to linear (or quasi-linear) functions of predictive rates, which can be practically restrictive for many applications including fairness. This paper develops a strategy for eliciting more flexible multiclass metrics defined by quadratic functions of rates, designed to reflect human preferences better. We show its application in eliciting quadratic violation-based group-fair metrics. Our strategy requires only relative preference feedback, is robust to noise, and achieves near-optimal query complexity. We further extend this strategy to eliciting polynomial metrics – thus broadening the use cases for metric elicitation. 

   more » « less
4. Lifelong Personalization via Gaussian Process Modeling for Long-Term HRI

   https://doi.org/10.3389/frobt.2021.683066  

   Spaulding, Samuel; Shen, Jocelyn; Park, Hae Won; Breazeal, Cynthia (June 2021, Frontiers in Robotics and AI)

   null (Ed.)

   Across a wide variety of domains, artificial agents that can adapt and personalize to users have potential to improve and transform how social services are provided. Because of the need for personalized interaction data to drive this process, long-term (or longitudinal) interactions between users and agents, which unfold over a series of distinct interaction sessions, have attracted substantial research interest. In recognition of the expanded scope and structure of a long-term interaction, researchers are also adjusting the personalization models and algorithms used, orienting toward “continual learning” methods, which do not assume a stationary modeling target and explicitly account for the temporal context of training data. In parallel, researchers have also studied the effect of “multitask personalization,” an approach in which an agent interacts with users over multiple different tasks contexts throughout the course of a long-term interaction and learns personalized models of a user that are transferrable across these tasks. In this paper, we unite these two paradigms under the framework of “Lifelong Personalization,” analyzing the effect of multitask personalization applied to dynamic, non-stationary targets. We extend the multi-task personalization approach to the more complex and realistic scenario of modeling dynamic learners over time, focusing in particular on interactive scenarios in which the modeling agent plays an active role in teaching the student whose knowledge the agent is simultaneously attempting to model. Inspired by the way in which agents use active learning to select new training data based on domain context, we augment a Gaussian Process-based multitask personalization model with a mechanism to actively and continually manage its own training data, allowing a modeling agent to remove or reduce the weight of observed data from its training set, based on interactive context cues. We evaluate this method in a series of simulation experiments comparing different approaches to continual and multitask learning on simulated student data. We expect this method to substantially improve learning in Gaussian Process models in dynamic domains, establishing Gaussian Processes as another flexible modeling tool for Long-term Human-Robot Interaction (HRI) Studies. 

   more » « less
5. Tensor-based reconstruction applied to regularized time-lapse data

   https://doi.org/10.1093/gji/ggac211  

   Popa, Jonathan; Minkoff, Susan E.; Lou, Yifei (June 2022, Geophysical Journal International)

   SUMMARY Repeatedly recording seismic data over a period of months or years is one way to identify trapped oil and gas and to monitor CO2 injection in underground storage reservoirs and saline aquifers. This process of recording data over time and then differencing the images assumes the recording of the data over a particular subsurface region is repeatable. In other words, the hope is that one can recover changes in the Earth when the survey parameters are held fixed between data collection times. Unfortunately, perfect experimental repeatability almost never occurs. Acquisition inconsistencies such as changes in weather (currents, wind) for marine seismic data are inevitable, resulting in source and receiver location differences between surveys at the very least. Thus, data processing aimed at improving repeatability between baseline and monitor surveys is extremely useful. One such processing tool is regularization (or binning) that aligns multiple surveys with different source or receiver configurations onto a common grid. Data binned onto a regular grid can be stored in a high-dimensional data structure called a tensor with, for example, x and y receiver coordinates and time as indices of the tensor. Such a higher-order data structure describing a subsection of the Earth often exhibits redundancies which one can exploit to fill in gaps caused by sampling the surveys onto the common grid. In fact, since data gaps and noise increase the rank of the tensor, seeking to recover the original data by reducing the rank (low-rank tensor-based completion) successfully fills in gaps caused by binning. The tensor nuclear norm (TNN) is defined by the tensor singular value decomposition (tSVD) which generalizes the matrix SVD. In this work we complete missing time-lapse data caused by binning using the alternating direction method of multipliers (or ADMM) to minimize the TNN. For a synthetic experiment with three parabolic events in which the time-lapse difference involves an amplitude increase in one of these events between baseline and monitor data sets, the binning and reconstruction algorithm (TNN-ADMM) correctly recovers this time-lapse change. We also apply this workflow of binning and TNN-ADMM reconstruction to a real marine survey from offshore Western Australia in which the binning onto a regular grid results in significant data gaps. The data after reconstruction varies continuously without the large gaps caused by the binning process. 

   more » « less