MAML-KT: Addressing Cold Start Problem in Knowledge Tracing for New Students via Few-Shot Model-Agnostic Meta Learning

• URL: http://arxiv.org/abs/2603.00137v1
• Date: Tue, 24 Feb 2026 05:49:23 GMT
• Title: MAML-KT: Addressing Cold Start Problem in Knowledge Tracing for New Students via Few-Shot Model-Agnostic Meta Learning
• Abstract summary: We introduce MAML-KT, a model-agnostic meta learning approach for rapid adaptation to new students.<n>MAML-KT achieves higher early accuracy than prior KT models in nearly all cold start conditions.<n>Overall, optimizing KT models for rapid adaptation reduces early prediction error for new students.
• Score: 2.8913142991383114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge tracing (KT) models are commonly evaluated by training on early interactions from all students and testing on later responses. While effective for measuring average predictive performance, this evaluation design obscures a cold start scenario that arises in deployment, where models must infer the knowledge state of previously unseen students from only a few initial interactions. Prior studies have shown that under this setting, standard empirically risk-minimized KT models such as DKT, DKVMN and SAKT exhibit substantially lower early accuracy than previously reported. We frame new-student performance prediction as a few-shot learning problem and introduce MAML-KT, a model-agnostic meta learning approach that learns an initialization optimized for rapid adaptation to new students using one or two gradient updates. We evaluate MAML-KT on ASSIST2009, ASSIST2015 and ASSIST2017 using a controlled cold start protocol that trains on a subset of students and tests on held-out learners across early interaction windows (questions 3-10 and 11-15), scaling cohort sizes from 10 to 50 students. Across datasets, MAML-KT achieves higher early accuracy than prior KT models in nearly all cold start conditions, with gains persisting as cohort size increases. On ASSIST2017, we observe a transient drop in early performance that coincides with many students encountering previously unseen skills. Further analysis suggests that these drops coincide with skill novelty rather than model instability, consistent with prior work on skill-level cold start. Overall, optimizing KT models for rapid adaptation reduces early prediction error for new students and provides a clearer lens for interpreting early accuracy fluctuations, distinguishing model limitations from genuine learning and knowledge acquisition dynamics.

Related papers

• Jointly Predicting Courses and Grades Using a Transformer-Based Model [0.0]
  This paper introduces a TRansformer for Academic Course-grade Estimation (TRACE)<n>Our approach encodes courses on a per-semester basis to capture the effects for an upcoming semester.<n>We demonstrate that predicting courses taken in addition to the grades in those courses leads to significant improvements in prediction quality.
  arXiv  Detail & Related papers  (2026-08-13T16:05:22Z)
• The Pre-Training Study of Expanded-SPLADE Models on Web Document Titles [0.08949202626090576]
  This paper studies effect of different pre-training datasets and pre-training options on the pre-trained models for retrieval fine-tuning.<n>Fine-tuned models of higher retrieval effectiveness at both unpruned and most strict pruned settings are mostly pre-trained on a general corpus.
  arXiv  Detail & Related papers  (2026-05-02T12:07:49Z)
• Uncertainty-Aware Knowledge Tracing Models [3.8834950760134657]
  We show an approach to add new capabilities to Knowledge Tracing models by capturing predictive uncertainty.<n>We show that uncertainty in KT models is informative and that this signal would be pedagogically useful for application in an educational learning platform.
  arXiv  Detail & Related papers  (2025-09-25T20:06:02Z)
• Cold Start Problem: An Experimental Study of Knowledge Tracing Models with New Students [4.7750095113157744]
  KnowledgeTracing (KT) involves predicting students' knowledge states based on their interactions with Intelligent Tutoring Systems (ITS)<n>Key challenge is the cold start problem, accurately predicting knowledge for new students with minimal interaction data.<n>We investigate cold start effects across three KT models: Deep Knowledge Tracing (DKT), Dynamic Key-Value Memory Networks (DKVMN), and Self-Attentive Knowledge Tracing (SAKT)<n>Results indicate all models initially struggle under cold start conditions but progressively improve with more interactions; SAKT shows higher initial accuracy yet still faces limitations.
  arXiv  Detail & Related papers  (2025-05-22T04:09:07Z)
• Improving Group Fairness in Knowledge Distillation via Laplace Approximation of Early Exits [0.0]
  We propose that leveraging Laplace approximation-based methods to obtain well-calibrated uncertainty estimates can also effectively reweight challenging instances.<n>To validate our claims, we benchmark our approach using a Bert-based model on the MultiNLI dataset.
  arXiv  Detail & Related papers  (2025-05-02T07:18:52Z)
• Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing [0.14999444543328289]
  Large Language Models (LLMs) have emerged as promising tools for knowledge tracing.<n>We present textitLLM-based Option-weighted Knowledge Tracing (LOKT), a framework that encodes the interaction histories of example learners in context.<n>LOKT enables scalable and cost-efficient inference, achieving strong performance even under strict token constraints.
  arXiv  Detail & Related papers  (2024-10-14T16:25:48Z)
• Few-Shot Load Forecasting Under Data Scarcity in Smart Grids: A Meta-Learning Approach [0.18641315013048293]
  This paper proposes adapting an established model-agnostic meta-learning algorithm for short-term load forecasting. The proposed method can rapidly adapt and generalize within any unknown load time series of arbitrary length. The proposed model is evaluated using a dataset of historical load consumption data from real-world consumers.
  arXiv  Detail & Related papers  (2024-06-09T18:59:08Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• MELEP: A Novel Predictive Measure of Transferability in Multi-Label ECG Diagnosis [1.3654846342364306]
  We introduce MELEP, a measure designed to estimate the effectiveness of knowledge transfer from a pre-trained model to a downstream ECG diagnosis task. Our experiments show that MELEP can predict the performance of pre-trained convolutional and recurrent deep neural networks, on small and imbalanced ECG data.
  arXiv  Detail & Related papers  (2023-10-27T14:57:10Z)
• ASPEST: Bridging the Gap Between Active Learning and Selective Prediction [56.001808843574395]
  Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples. In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
  arXiv  Detail & Related papers  (2023-04-07T23:51:07Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need [84.3507610522086]
  Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting old ones. Recent pre-training has achieved substantial progress, making vast pre-trained models (PTMs) accessible for CIL. We argue that the core factors in CIL are adaptivity for model updating and generalizability for knowledge transferring.
  arXiv  Detail & Related papers  (2023-03-13T17:59:02Z)
• CLIPood: Generalizing CLIP to Out-of-Distributions [73.86353105017076]
  Contrastive language-image pre-training (CLIP) models have shown impressive zero-shot ability, but the further adaptation of CLIP on downstream tasks undesirably degrades OOD performances. We propose CLIPood, a fine-tuning method that can adapt CLIP models to OOD situations where both domain shifts and open classes may occur on unseen test data. Experiments on diverse datasets with different OOD scenarios show that CLIPood consistently outperforms existing generalization techniques.
  arXiv  Detail & Related papers  (2023-02-02T04:27:54Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Monotonicity in practice of adaptive testing [0.0]
  This article evaluates Bayesian network models used for computerized adaptive testing and learned with a recently proposed monotonicity gradient algorithm. The quality of methods is empirically evaluated on a large data set of the Czech National Mathematics exam.
  arXiv  Detail & Related papers  (2020-09-15T10:55:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.