arXiv subjects

Min Chi

Publications and source records attributed to Min Chi.

35 records · Page 2Linked to original sources

arXiv2023

Metacognition and Motivation: The Role of Time-Awareness in Preparation for Future Learning

In this work, we investigate how two factors, metacognitive skills and motivation, would impact student learning across domains. More specifically, our primary goal is to identify the critical, yet robust, interaction patterns of these two factors that would contribute to students' performance in learning logic first and then their performance on a subsequent new domain, probability. We are concerned with two types of metacognitive skills: strategy-awareness and time-awareness, that is, which problem-solving strategy to use and when to use it. Our data were collected from 495 participants across three consecutive semesters, and our results show that the only students who consistently outperform their peers across both domains are those who are not only highly motivated but also strategy-aware and time-aware.

cs.HC↗

arXiv2023

Assessing Competency Using Metacognition and Motivation: The Role of Time-Awareness in Preparation for Future Learning

One fundamental goal of learning is preparation for future learning (PFL) and being able to extend acquired skills and problem-solving strategies to different domains and environments. While substantial research has shown that PFL can be accelerated by obtaining metacognitive skills or influenced by the individual's motivation, no prior work investigated whether the interaction of the two factors could assess students' competency for PFL. In this chapter, we tackle this research question in one type of highly interactive e-learning environment, intelligent tutoring systems. More specifically, we investigate whether the combination of metacognitive skills and motivation would assess students' learning abilities in logic, and their competence to extend these abilities to a subsequent domain, probability.

cs.HC↗

arXiv2023

HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare

Reinforcement learning (RL) has been extensively researched for enhancing human-environment interactions in various human-centric tasks, including e-learning and healthcare. Since deploying and evaluating policies online are high-stakes in such tasks, off-policy evaluation (OPE) is crucial for inducing effective policies. In human-centric environments, however, OPE is challenging because the underlying state is often unobservable, while only aggregate rewards can be observed (students' test scores or whether a patient is released from the hospital eventually). In this work, we propose a human-centric OPE (HOPE) to handle partial observability and aggregated rewards in such environments. Specifically, we reconstruct immediate rewards from the aggregated rewards considering partial observability to estimate expected total returns. We provide a theoretical bound for the proposed method, and we have conducted extensive experiments in real-world human-centric tasks, including sepsis treatments and an intelligent tutoring system. Our approach reliably predicts the returns of different policies and outperforms state-of-the-art benchmarks using both standard validation methods and human-centric significance tests.

cs.LG↗

arXiv2023

Variational Latent Branching Model for Off-Policy Evaluation

Model-based methods have recently shown great potential for off-policy evaluation (OPE); offline trajectories induced by behavioral policies are fitted to transitions of Markov decision processes (MDPs), which are used to rollout simulated trajectories and estimate the performance of policies. Model-based OPE methods face two key challenges. First, as offline trajectories are usually fixed, they tend to cover limited state and action space. Second, the performance of model-based methods can be sensitive to the initialization of their parameters. In this work, we propose the variational latent branching model (VLBM) to learn the transition function of MDPs by formulating the environmental dynamics as a compact latent space, from which the next states and rewards are then sampled. Specifically, VLBM leverages and extends the variational inference framework with the recurrent state alignment (RSA), which is designed to capture as much information underlying the limited training data, by smoothing out the information flow between the variational (encoding) and generative (decoding) part of VLBM. Moreover, we also introduce the branching architecture to improve the model's robustness against randomly initialized model weights. The effectiveness of the VLBM is evaluated on the deep OPE (DOPE) benchmark, from which the training trajectories are designed to result in varied coverage of the state-action space. We show that the VLBM outperforms existing state-of-the-art OPE methods in general.

cs.LG↗

arXiv2022

Investigating the Impact of Backward Strategy Learning in a Logic Tutor: Aiding Subgoal Learning towards Improved Problem Solving

Learning to derive subgoals reduces the gap between experts and students and makes students prepared for future problem solving. Researchers have explored subgoal labeled instructional materials with explanations in traditional problem solving and within tutoring systems to help novices learn to subgoal. However, only a little research is found on problem-solving strategies in relationship with subgoal learning. Also, these strategies are under-explored within computer-based tutors and learning environments. Backward problem-solving strategy is closely related to the process of subgoaling, where problem solving iteratively refines the goal into a new subgoal to reduce difficulty. In this paper, we explore a training strategy for backward strategy learning within an intelligent logic tutor that teaches logic proof construction. The training session involved backward worked examples (BWE) and problem-solving (BPS) to help students learn backward strategy towards improving their subgoaling and problem-solving skills. To evaluate the training strategy, we analyzed students' 1) experience with and engagement in learning backward strategy, 2) performance, and 3) proof construction approaches in new problems that they solved independently without tutor help after each level of training and in post-test. Our results showed that, when new problems were given to solve without any tutor help, students who were trained with both BWE and BPS outperformed students who received none of the treatment or only BWE during training. Additionally, students trained with both BWE and BPS derived subgoals during proof construction with significantly higher efficiency than the other two groups.

cs.CY↗

arXiv2022

A Multicriteria Evaluation for Data-Driven Programming Feedback Systems: Accuracy, Effectiveness, Fallibility, and Students' Response

Data-driven programming feedback systems can help novices to program in the absence of a human tutor. Prior evaluations showed that these systems improve learning in terms of test scores, or task completion efficiency. However, crucial aspects which can impact learning or reveal insights important for future improvement of such systems are ignored in these evaluations. These aspects include inherent fallibility of current state-of-the-art, students' programming behavior in response to correct/incorrect feedback, and effective/ineffective system components. Consequently, a great deal of knowledge is yet to be discovered about such systems. In this paper, we apply a multi-criteria evaluation with 5 criteria on a data-driven feedback system integrated within a block-based novice programming environment. Each criterion in the evaluation reveals a unique pivotal aspect of the system: 1) How accurate the feedback system is; 2) How it guides students throughout programming tasks; 3) How it helps students in task completion; 4) What happens when it goes wrong; and 5) How students respond generally to the system. Our evaluation results showed that the system was helpful to students due to its effective design and feedback representation despite being fallible. However, novices can be negatively impacted by this fallibility due to high reliance and lack of self-evaluation. The negative impacts include increased working time, implementation, or submission of incorrect/partially correct solutions. The evaluation results reinforced the necessity of multi-criteria system evaluations while revealing important insights helpful to ensuring proper usage of data-driven feedback systems, designing fallibility mitigation steps, and driving research for future improvement.

cs.CY↗

arXiv2022

Reconstructing Missing EHRs Using Time-Aware Within- and Cross-Visit Information for Septic Shock Early Prediction

Real-world Electronic Health Records (EHRs) are often plagued by a high rate of missing data. In our EHRs, for example, the missing rates can be as high as 90% for some features, with an average missing rate of around 70% across all features. We propose a Time-Aware Dual-Cross-Visit missing value imputation method, named TA-DualCV, which spontaneously leverages multivariate dependencies across features and longitudinal dependencies both within- and cross-visit to maximize the information extracted from limited observable records in EHRs. Specifically, TA-DualCV captures the latent structure of missing patterns across measurements of different features and it also considers the time continuity and capture the latent temporal missing patterns based on both time-steps and irregular time-intervals. TA-DualCV is evaluated using three large real-world EHRs on two types of tasks: an unsupervised imputation task by varying mask rates up to 90% and a supervised 24-hour early prediction of septic shock using Long Short-Term Memory (LSTM). Our results show that TA-DualCV performs significantly better than all of the existing state-of-the-art imputation baselines, such as DETROIT and TAME, on both types of tasks.

cs.LG↗

arXiv2022

Enhancing a Student Productivity Model for Adaptive Problem-Solving Assistance

Research on intelligent tutoring systems has been exploring data-driven methods to deliver effective adaptive assistance. While much work has been done to provide adaptive assistance when students seek help, they may not seek help optimally. This had led to the growing interest in proactive adaptive assistance, where the tutor provides unsolicited assistance upon predictions of struggle or unproductivity. Determining when and whether to provide personalized support is a well-known challenge called the assistance dilemma. Addressing this dilemma is particularly challenging in open-ended domains, where there can be several ways to solve problems. Researchers have explored methods to determine when to proactively help students, but few of these methods have taken prior hint usage into account. In this paper, we present a novel data-driven approach to incorporate students' hint usage in predicting their need for help. We explore its impact in an intelligent tutor that deals with the open-ended and well-structured domain of logic proofs. We present a controlled study to investigate the impact of an adaptive hint policy based on predictions of HelpNeed that incorporate students' hint usage. We show empirical evidence to support that such a policy can save students a significant amount of time in training, and lead to improved posttest results, when compared to a control without proactive interventions. We also show that incorporating students' hint usage significantly improves the adaptive hint policy's efficacy in predicting students' HelpNeed, thereby reducing training unproductivity, reducing possible help avoidance, and increasing possible help appropriateness (a higher chance of receiving help when it was likely to be needed). We conclude with suggestions on the domains that can benefit from this approach as well as the requirements for adoption.

cs.AI↗

arXiv2022

Code-DKT: A Code-based Knowledge Tracing Model for Programming Tasks

Knowledge tracing (KT) models are a popular approach for predicting students' future performance at practice problems using their prior attempts. Though many innovations have been made in KT, most models including the state-of-the-art Deep KT (DKT) mainly leverage each student's response either as correct or incorrect, ignoring its content. In this work, we propose Code-based Deep Knowledge Tracing (Code-DKT), a model that uses an attention mechanism to automatically extract and select domain-specific code features to extend DKT. We compared the effectiveness of Code-DKT against Bayesian and Deep Knowledge Tracing (BKT and DKT) on a dataset from a class of 50 students attempting to solve 5 introductory programming assignments. Our results show that Code-DKT consistently outperforms DKT by 3.07-4.00% AUC across the 5 assignments, a comparable improvement to other state-of-the-art domain-general KT models over DKT. Finally, we analyze problem-specific performance through a set of case studies for one assignment to demonstrate when and how code features improve Code-DKT's predictions.

cs.SE↗

arXiv2022

Making a (Counterfactual) Difference One Rationale at a Time

Rationales, snippets of extracted text that explain an inference, have emerged as a popular framework for interpretable natural language processing (NLP). Rationale models typically consist of two cooperating modules: a selector and a classifier with the goal of maximizing the mutual information (MMI) between the "selected" text and the document label. Despite their promises, MMI-based methods often pick up on spurious text patterns and result in models with nonsensical behaviors. In this work, we investigate whether counterfactual data augmentation (CDA), without human assistance, can improve the performance of the selector by lowering the mutual information between spurious signals and the document label. Our counterfactuals are produced in an unsupervised fashion using class-dependent generative models. From an information theoretic lens, we derive properties of the unaugmented dataset for which our CDA approach would succeed. The effectiveness of CDA is empirically evaluated by comparing against several baselines including an improved MMI-based rationale schema on two multi aspect datasets. Our results show that CDA produces rationales that better capture the signal of interest.

cs.CL↗

arXiv2021

Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning

Deep Reinforcement Learning (DRL) has shown outstanding performance on inducing effective action policies that maximize expected long-term return on many complex tasks. Much of DRL work has been focused on sequences of events with discrete time steps and ignores the irregular time intervals between consecutive events. Given that in many real-world domains, data often consists of temporal sequences with irregular time intervals, and it is important to consider the time intervals between temporal events to capture latent progressive patterns of states. In this work, we present a general Time-Aware RL framework: Time-aware Q-Networks (TQN), which takes into account physical time intervals within a deep RL framework. TQN deals with time irregularity from two aspects: 1) elapsed time in the past and an expected next observation time for time-aware state approximation, and 2) action time window for the future for time-aware discounting of rewards. Experimental results show that by capturing the underlying structures in the sequences with time irregularities from both aspects, TQNs significantly outperform DQN in four types of contexts with irregular time intervals. More specifically, our results show that in classic RL tasks such as CartPole and MountainCar and Atari benchmark with randomly segmented time intervals, time-aware discounting alone is more important while in the real-world tasks such as nuclear reactor operation and septic patient treatment with intrinsic time intervals, both time-aware state and time-aware discounting are crucial. Moreover, to improve the agent's learning capacity, we explored three boosting methods: Double networks, Dueling networks, and Prioritized Experience Replay, and our results show that for the two real-world tasks, combining all three boosting methods with TQN is especially effective.

cs.LG↗

arXiv2021

InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem

The temporal Credit Assignment Problem (CAP) is a well-known and challenging task in AI. While Reinforcement Learning (RL), especially Deep RL, works well when immediate rewards are available, it can fail when only delayed rewards are available or when the reward function is noisy. In this work, we propose delegating the CAP to a Neural Network-based algorithm named InferNet that explicitly learns to infer the immediate rewards from the delayed rewards. The effectiveness of InferNet was evaluated on two online RL tasks: a simple GridWorld and 40 Atari games; and two offline RL tasks: GridWorld and a real-life Sepsis treatment task. For all tasks, the effectiveness of using the InferNet inferred rewards is compared against the immediate and the delayed rewards with two settings: with noisy rewards and without noise. Overall, our results show that the effectiveness of InferNet is robust against noisy reward functions and is an effective add-on mechanism for solving temporal CAP in a wide range of RL tasks, from classic RL simulation environments to a real-world RL problem and for both online and offline learning.

cs.LG↗

arXiv2021

The Impact of Looking Further Ahead: A Comparison of Two Data-driven Unsolicited Hint Types on Performance in an Intelligent Data-driven Logic Tutor

Research has shown assistance can provide many benefits to novices lacking the mental models needed for problem solving in a new domain. However, varying approaches to assistance, such as subgoals and next-step hints, have been implemented with mixed results. Next-Step hints are common in data-driven tutors due to their straightforward generation from historical student data, as well as research showing positive impacts on student learning. However, there is a lack of research exploring the possibility of extending data-driven methods to provide higher-level assistance. Therefore, we modified our data-driven Next-Step hint generator to provide Waypoints, hints that are a few steps ahead, representing problem-solving subgoals. We hypothesized that Waypoints would benefit students with high prior knowledge, and that Next-Step hints would most benefit students with lower prior knowledge. In this study, we investigated the influence of data-driven hint type, Waypoints versus Next-Step hints, on student learning in a logic proof tutoring system, Deep Thought, in a discrete mathematics course. We found that Next-Step hints were more beneficial for the majority of students in terms of time, efficiency, and accuracy on the posttest. However, higher totals of successfully used Waypoints were correlated with improvements in efficiency and time in the posttest. These results suggest that Waypoint hints could be beneficial, but more scaffolding may be needed to help students follow them.

cs.HC↗

arXiv2021

TC-DTW: Accelerating Multivariate Dynamic Time Warping Through Triangle Inequality and Point Clustering

Dynamic time warping (DTW) plays an important role in analytics on time series. Despite the large body of research on speeding up univariate DTW, the method for multivariate DTW has not been improved much in the last two decades. The most popular algorithm used today is still the one developed seventeen years ago. This paper presents a solution that, as far as we know, for the first time consistently outperforms the classic multivariate DTW algorithm across dataset sizes, series lengths, data dimensions, temporal window sizes, and machines. The new solution, named TC-DTW, introduces Triangle Inequality and Point Clustering into the algorithm design on lower bound calculations for multivariate DTW. In experiments on DTW-based nearest neighbor finding, the new solution avoids as much as 98% (60% average) DTW distance calculations and yields as much as 25X (7.5X average) speedups.

cs.LG↗

arXiv2020

An Adversarial Domain Separation Framework for Septic Shock Early Prediction Across EHR Systems

Modeling patient disease progression using Electronic Health Records (EHRs) is critical to assist clinical decision making. While most of prior work has mainly focused on developing effective disease progression models using EHRs collected from an individual medical system, relatively little work has investigated building robust yet generalizable diagnosis models across different systems. In this work, we propose a general domain adaptation (DA) framework that tackles two categories of discrepancies in EHRs collected from different medical systems: one is caused by heterogeneous patient populations (covariate shift) and the other is caused by variations in data collection procedures (systematic bias). Prior research in DA has mainly focused on addressing covariate shift but not systematic bias. In this work, we propose an adversarial domain separation framework that addresses both categories of discrepancies by maintaining one globally-shared invariant latent representation across all systems} through an adversarial learning process, while also allocating a domain-specific model for each system to extract local latent representations that cannot and should not be unified across systems. Moreover, our proposed framework is based on variational recurrent neural network (VRNN) because of its ability to capture complex temporal dependencies and handling missing values in time-series data. We evaluate our framework for early diagnosis of an extremely challenging condition, septic shock, using two real-world EHRs from distinct medical systems in the U.S. The results show that by separating globally-shared from domain-specific representations, our framework significantly improves septic shock early prediction performance in both EHRs and outperforms the current state-of-the-art DA models.

cs.LG↗

arXiv2020

Avoiding Help Avoidance: Using Interface Design Changes to Promote Unsolicited Hint Usage in an Intelligent Tutor

Within intelligent tutoring systems, considerable research has investigated hints, including how to generate data-driven hints, what hint content to present, and when to provide hints for optimal learning outcomes. However, less attention has been paid to how hints are presented. In this paper, we propose a new hint delivery mechanism called "Assertions" for providing unsolicited hints in a data-driven intelligent tutor. Assertions are partially-worked example steps designed to appear within a student workspace, and in the same format as student-derived steps, to show students a possible subgoal leading to the solution. We hypothesized that Assertions can help address the well-known hint avoidance problem. In systems that only provide hints upon request, hint avoidance results in students not receiving hints when they are needed. Our unsolicited Assertions do not seek to improve student help-seeking, but rather seek to ensure students receive the help they need. We contrast Assertions with Messages, text-based, unsolicited hints that appear after student inactivity. Our results show that Assertions significantly increase unsolicited hint usage compared to Messages. Further, they show a significant aptitude-treatment interaction between Assertions and prior proficiency, with Assertions leading students with low prior proficiency to generate shorter (more efficient) posttest solutions faster. We also present a clustering analysis that shows patterns of productive persistence among students with low prior knowledge when the tutor provides unsolicited help in the form of Assertions. Overall, this work provides encouraging evidence that hint presentation can significantly impact how students use them and using Assertions can be an effective way to address help avoidance.

cs.AI↗

arXiv2020

Extending the Hint Factory for the assistance dilemma: A novel, data-driven HelpNeed Predictor for proactive problem-solving help

Determining when and whether to provide personalized support is a well-known challenge called the assistance dilemma. A core problem in solving the assistance dilemma is the need to discover when students are unproductive so that the tutor can intervene. Such a task is particularly challenging for open-ended domains, even those that are well-structured with defined principles and goals. In this paper, we present a set of data-driven methods to classify, predict, and prevent unproductive problem-solving steps in the well-structured open-ended domain of logic. This approach leverages and extends the Hint Factory, a set of methods that leverages prior student solution attempts to build data-driven intelligent tutors. We present a HelpNeed classification, that uses prior student data to determine when students are likely to be unproductive and need help learning optimal problem-solving strategies. We present a controlled study to determine the impact of an Adaptive pedagogical policy that provides proactive hints at the start of each step based on the outcomes of our HelpNeed predictor: productive vs. unproductive. Our results show that the students in the Adaptive condition exhibited better training behaviors, with lower help avoidance, and higher help appropriateness (a higher chance of receiving help when it was likely to be needed), as measured using the HelpNeed classifier, when compared to the Control. Furthermore, the results show that the students who received Adaptive hints based on HelpNeed predictions during training significantly outperform their Control peers on the posttest, with the former producing shorter, more optimal solutions in less time. We conclude with suggestions on how these HelpNeed methods could be applied in other well-structured open-ended domains.

cs.AI↗