arXiv research

Study predicts academic achievement using students' support networks.

Predicts student performance in interactive online question pools using GNNs.

Bayesian Causal Forests model assesses part-time work's impact on student growth.

We propose a novel way to train ranking models, such as recommender systems, that are both effective and efficient. Knowledge distillation (KD) was shown to be successful in image recognition to achieve both effectiveness and efficiency. We propose a KD technique for learning to rank problems, called \emph{ranking dist…

A new distillation method transfers channel information from teacher to student.

We propose a multimodal approach for detection of students' behavioral engagement states (i.e., On-Task vs. Off-Task), based on three unobtrusive modalities: Appearance, Context-Performance, and Mouse. Final behavioral engagement states are achieved by fusing modality-specific classifiers at the decision level. Various…

Proposes RaT to mitigate bias in student-teacher estimation.

Deep neural networks bring in impressive accuracy in various applications, but the success often relies on the heavy network architecture. Taking well-trained heavy networks as teachers, classical teacher-student learning paradigm aims to learn a student network that is lightweight yet accurate. In this way, a portable…

Driven by the goal to enable sleep apnea monitoring and machine learning-based detection at home with small mobile devices, we investigate whether interpretation-based indirect knowledge transfer can be used to create classifiers with acceptable performance. Interpretation-based indirect knowledge transfer means that a…

A new teacher-class network method compresses DNNs by distributing knowledge to multiple student networks.

We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. On robustness test sets, i…

Performing knowledge transfer from a large teacher network to a smaller student is a popular task in modern deep learning applications. However, due to growing dataset sizes and stricter privacy regulations, it is increasingly common not to have access to the data that was used to train the teacher. We propose a novel …

Recently, consistency-based methods have achieved state-of-the-art results in semi-supervised learning (SSL). These methods always involve two roles, an explicit or implicit teacher model and a student model, and penalize predictions under different perturbations by a consistency constraint. However, the weights of the…

Study uses ML and causal analysis to predict student performance factors.

Access to high-quality education at scale is limited by the difficulty of providing student feedback on open-ended assignments in structured domains like computer programming, graphics, and short response questions. This problem has proven to be exceptionally difficult: for humans, it requires large amounts of manual w…

Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural networks in the teacher-student setup, where one network, the student, is trained…

Private business schools in India face a common problem of selecting quality students for their MBA programs to achieve the desired placement percentage. Generally, such data sets are biased towards one class, i.e., imbalanced in nature. And learning from the imbalanced dataset is a difficult proposition. This paper pr…

Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a teacher-student setup, where one network, the student, is trained using stochastic gradient de…

One of the important measures of quality of education is the performance of students in the academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students are learning and how to improve their performance ahead of time using data mining…

Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress these networks, and a popular method is knowledge distillation, where a large (teac…

This work proposes a student-teacher network for predicting hospital admission locations.

Meta Pseudo Labels boosts image classification accuracy to 90.2%.

The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size. However, the efficacy of pruning based approaches has since been called into question. In this paper, we turn to distillation for model compression---specifically,…

Paper introduces efficient uncertainty estimation in LLMs without multiple forward passes.

Paper analyzes how neural networks learn from a teacher in a specific setting.

A VB method for high-dimensional regression with student-t priors achieves nearly optimal performance and computational efficiency.

The paper reveals three mechanisms for weak-to-strong generalization.

Machine learning methods tend to outperform traditional statistical models at prediction. In the prediction of academic achievement, ML models have not shown substantial improvement over logistic regression. So far, these results have almost entirely focused on college achievement, due to the availability of administra…

Study finds different active learning techniques better for various learning objectives.

This paper explores the suitability of using automatically discovered topics from MOOC discussion forums for modelling students' academic abilities. The Rasch model from psychometrics is a popular generative probabilistic model that relates latent student skill, latent item difficulty, and observed student-item respons…

Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial training to minimize the discrepancy between distributions of output from two net…

SiamJEPA uses Siamese student encoders to improve JEPA-based representation learning.

We study heterogeneity in the effect of a mindset intervention on student-level performance through an observational dataset from the National Study of Learning Mindsets (NSLM). Our analysis uses machine learning (ML) to address the following associated problems: assessing treatment group overlap and covariate balance,…

Improved machine learning models outperform their simpler counterparts by using imperfect labels.

We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \emph{over-realized}: at each layer $l$, the number $n_l$ of student nodes is more than that ($m_l$) of teacher. Under mild conditions…

The teacher-student (T/S) learning has been shown to be effective for a variety of problems such as domain adaptation and model compression. One shortcoming of the T/S learning is that a teacher model, not always perfect, sporadically produces wrong guidance in form of posterior probabilities that misleads the student …

Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing approaches use either the training data or meta-data extracted from it in order to train the Student. However, accessing the dataset on which …

When a bilingual student learns to solve word problems in math, we expect the student to be able to solve these problem in both languages the student is fluent in,even if the math lessons were only taught in one language. However, current representations in machine learning are language dependent. In this work, we pres…

In this paper, we present a deep neural network (DNN) training approach called the "DeepMimic" training method. Enormous amounts of data are available nowadays for training usage. Yet, only a tiny portion of these data is manually labeled, whereas almost all of the data are unlabeled. The training approach presented ut…

We adopt a multi-view approach for analyzing two knowledge transfer settings---learning using privileged information (LUPI) and distillation---in a common framework. Under reasonable assumptions about the complexities of hypothesis spaces, and being optimistic about the expected loss achievable by the student (in disti…

New method improves generative modeling on convex domains using regularized mirror maps and Student-t priors.

Randomly sampled interpolators achieve zero generalization error with enough data.

BCF models estimate causal effects on multiple outcomes in TIMSS data.

The study uses Hidden Markov Models to analyze student enrollment patterns and academic performance.

Method transfers feature representation from large to small models using perception coherence.

The paper characterizes the efficiency of transferring knowledge from a teacher to a student classifier over finite domains.

Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful analysis of the model may therefore reveal sensitive information. To address this problem, we demon…

This paper presents a method to train a public model with private data using GANs and differential privacy.