Related papers: Disentangling Learning from Judgment: Representati…
Computational learning approaches to solving visual reasoning tests, such as Raven's Progressive Matrices (RPM), critically depend on the ability to identify the visual concepts used in the test (i.e., the representation) as well as the…
Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…
Mixed-effects models fit to observational practice data are widely used in learning analytics to estimate student-level variation in initial knowledge and learning rate, and the resulting estimates increasingly inform substantive claims…
Standardized Student Evaluation of Teaching often suffer from low reliability, restricted response options, and response distortion. Existing machine learning methods that mine open-ended comments usually reduce feedback to binary…
The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this…
Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations…
Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors over time, prior work…
The knowledge that humans hold about a problem often extends far beyond a set of training data and output labels. While the success of deep learning mostly relies on supervised training, important properties cannot be inferred efficiently…
Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is…
The purpose of this paper is to determine potential identifiers of students' academic success in foundation mathematics course from the data logs of an intelligent tutor. A cross-sectional study design was used. A sample of 58 records was…
Manually grading the Response to Text Assessment (RTA) is labor intensive. Therefore, an automatic method is being developed for scoring analytical writing when the RTA is administered in large numbers of classrooms. Our long-term goal is…
Recommendation models can effectively estimate underlying user interests and predict one's future behaviors by factorizing an observed user-item rating matrix into products of two sets of latent factors. However, the user-specific embedding…
Disentangled representation has been widely explored in many fields due to its maximal compactness, interpretability and versatility. Recommendation system also needs disentanglement to make representation more explainable and general for…
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…
Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model…
Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…
Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to…
The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed several challenges. However, they still struggle with…
Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…
This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence…