Temporal Smoothness Doubly Robust Learning for Debiased Knowledge Tracing

2026-05-07

AI Summary

This study addresses severe selection bias in knowledge tracing caused by non-random exercise recommendations and student self-selection, which leads to biased ability estimates and error accumulation. To mitigate this, the work introduces doubly robust estimation into knowledge tracing for the first time, proposing a correction framework that integrates propensity score modeling with outcome imputation. It further innovatively incorporates temporal smoothing regularization to suppress variance growth in sequential ability estimation. Theoretical analysis demonstrates that temporal smoothing plays a crucial role in controlling estimation variance, thereby achieving a unified balance between unbiasedness and low variance. Extensive experiments on multiple real-world educational datasets show that the proposed method significantly improves the prediction accuracy of mainstream knowledge tracing models, validating the effectiveness of both bias correction and temporal smoothing.

Abstract

Knowledge Tracing (KT) is fundamental to intelligent education systems, yet relies on educational logs that are selectively observed. The non-random nature of exercise recommendations and student choices inevitably induces severe selection bias. Most existing KT methods neglect this issue, training on observed logs using standard empirical risk, which yields biased mastery estimates and accumulates errors in subsequent recommendations. To address this, we introduce a doubly robust (DR) formulation for KT that integrates a propensity model with an error imputation model, theoretically guaranteeing unbiasedness if either model is accurate. Beyond unbiasedness, in the sequential setting of KT, we identify that the estimator's performance is compromised by variance-dependent stochastic deviations that accumulate over time, thereby causing training instability and limiting performance. To mitigate this, we derive a generalization bound that explicitly characterizes the impact of estimator variance and identifies temporal smoothness as a key factor in controlling it. Building on these theoretical insights, we propose the Temporal Smoothness Doubly Robust (TSDR) framework. TSDR jointly optimizes the KT predictor and the imputation model with a smoothness regularizer, effectively reducing variance while preserving the unbiasedness guarantee of DR. Experiments on multiple real-world benchmarks demonstrate that TSDR consistently enhances various state-of-the-art KT backbones, underscoring the vital role of principled bias correction in KT.

Problem

• selection bias
• knowledge tracing
• temporal smoothness
• doubly robust learning
• variance accumulation

Innovation

• Doubly Robust Learning
• Temporal Smoothness
• Selection Bias
• Knowledge Tracing
• Variance Reduction