An Empirical Study of Knowledge Distillation for Code Understanding Tasks

• URL: http://arxiv.org/abs/2508.15423v1
• Date: Thu, 21 Aug 2025 10:24:48 GMT
• Title: An Empirical Study of Knowledge Distillation for Code Understanding Tasks
• Authors: Ruiqi Wang, Zezhou Yang, Cuiyun Gao, Xin Xia, Qing Liao,
• Abstract summary: Knowledge distillation (KD) addresses limitations by transferring knowledge from large teacher models to compact student models.<n>This paper systematically investigates the effectiveness and usage of KD in code understanding tasks.
• Score: 19.64130505527951
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency. Knowledge distillation (KD), a promising model compression and acceleration technique, addresses these limitations by transferring knowledge from large teacher models to compact student models, enabling efficient inference while preserving most of the teacher models' capabilities. While this technique has shown remarkable success in natural language processing and computer vision domains, its potential for code understanding tasks remains largely underexplored. In this paper, we systematically investigate the effectiveness and usage of KD in code understanding tasks. Our study encompasses two popular types of KD methods, i.e., logit-based and feature-based KD methods, experimenting across eight student models and two teacher PLMs from different domains on three downstream tasks. The experimental results indicate that KD consistently offers notable performance boosts across student models with different sizes compared with standard fine-tuning. Notably, code-specific PLM demonstrates better effectiveness as the teacher model. Among all KD methods, the latest feature-based KD methods exhibit superior performance, enabling student models to retain up to 98% teacher performance with merely 5% parameters. Regarding student architecture, our experiments reveal that similarity with teacher architecture does not necessarily lead to better performance. We further discuss the efficiency and behaviors in the KD process and inference, summarize the implications of findings, and identify promising future directions.

Related papers

• MoKD: Multi-Task Optimization for Knowledge Distillation [33.447451819037106]
  Two key challenges in Knowledge Distillation (KD) are balancing learning from the teacher's guidance and the task objective.<n>We propose Multi-Task Optimization for Knowledge Distillation (MoKD)<n>MoKD reformulates KD as a multi-objective optimization problem, enabling better balance between objectives.
  arXiv  Detail & Related papers  (2025-05-13T02:13:39Z)
• Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling [81.00825302340984]
  We introduce Speculative Knowledge Distillation (SKD) to generate high-quality training data on-the-fly.<n>In SKD, the student proposes tokens, and the teacher replaces poorly ranked ones based on its own distribution.<n>We evaluate SKD on various text generation tasks, including translation, summarization, math, and instruction following.
  arXiv  Detail & Related papers  (2024-10-15T06:51:25Z)
• Revisiting Knowledge Distillation for Autoregressive Language Models [88.80146574509195]
  We propose a simple yet effective adaptive teaching approach (ATKD) to improve the knowledge distillation (KD) The core of ATKD is to reduce rote learning and make teaching more diverse and flexible. Experiments on 8 LM tasks show that, with the help of ATKD, various baseline KD methods can achieve consistent and significant performance gains.
  arXiv  Detail & Related papers  (2024-02-19T07:01:10Z)
• DistiLLM: Towards Streamlined Distillation for Large Language Models [53.46759297929675]
  DistiLLM is a more effective and efficient KD framework for auto-regressive language models. DisiLLM comprises two components: (1) a novel skew Kullback-Leibler divergence loss, where we unveil and leverage its theoretical properties, and (2) an adaptive off-policy approach designed to enhance the efficiency in utilizing student-generated outputs.
  arXiv  Detail & Related papers  (2024-02-06T11:10:35Z)
• Comparative Knowledge Distillation [102.35425896967791]
  Traditional Knowledge Distillation (KD) assumes readily available access to teacher models for frequent inference. We propose Comparative Knowledge Distillation (CKD), which encourages student models to understand the nuanced differences in a teacher model's interpretations of samples. CKD consistently outperforms state of the art data augmentation and KD techniques.
  arXiv  Detail & Related papers  (2023-11-03T21:55:33Z)
• Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization [29.113990037893597]
  Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) performance by transferring the knowledge from a larger model (a teacher) Existing KD techniques do not mitigate noise in the teacher's output: noisy behaviour distracts the student from learning more useful teacher. We propose a new KD method that addresses these problems compared to previous techniques.
  arXiv  Detail & Related papers  (2022-12-12T16:00:20Z)
• Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation [70.92135839545314]
  We propose the dynamic prior knowledge (DPK), which integrates part of teacher's features as the prior knowledge before the feature distillation. Our DPK makes the performance of the student model positively correlated with that of the teacher model, which means that we can further boost the accuracy of students by applying larger teachers.
  arXiv  Detail & Related papers  (2022-06-13T11:52:13Z)
• Dynamic Knowledge Distillation for Pre-trained Language Models [32.63862596630663]
  We explore whether a dynamic knowledge distillation that empowers the student to adjust the learning procedure according to its competency. Experimental results show that proper selection of teacher model can boost the performance of student model. We find dynamic knowledge distillation is promising and provide discussions on potential future directions.
  arXiv  Detail & Related papers  (2021-09-23T11:02:24Z)
• Knowledge Distillation Beyond Model Compression [13.041607703862724]
  Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or ensemble of models (teacher) In this study, we provide an extensive study on nine different KD methods which covers a broad spectrum of approaches to capture and transfer knowledge.
  arXiv  Detail & Related papers  (2020-07-03T19:54:04Z)
• Heterogeneous Knowledge Distillation using Information Flow Modeling [82.83891707250926]
  We propose a novel KD method that works by modeling the information flow through the various layers of the teacher model. The proposed method is capable of overcoming the aforementioned limitations by using an appropriate supervision scheme during the different phases of the training process.
  arXiv  Detail & Related papers  (2020-05-02T06:56:56Z)

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.