SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval

• URL: http://arxiv.org/abs/2508.00546v1
• Date: Fri, 01 Aug 2025 11:39:32 GMT
• Title: SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval
• Authors: Wenchao Gu, Zongyi Lyu, Yanlin Wang, Hongyu Zhang, Cuiyun Gao, Michael R. Lyu,
• Abstract summary: We propose a framework, which adopts Self-AdaPtive Model Distillation for Efficient CodE Retrieval, named SPENCER.<n>We show that the combination of dual-encoder and cross-encoder improves overall performance compared to solely dual-encoder-based models for code retrieval.
• Score: 46.194566677039525
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Code retrieval aims to provide users with desired code snippets based on users' natural language queries. With the development of deep learning technologies, adopting pre-trained models for this task has become mainstream. Considering the retrieval efficiency, most of the previous approaches adopt a dual-encoder for this task, which encodes the description and code snippet into representation vectors, respectively. However, the model structure of the dual-encoder tends to limit the model's performance, since it lacks the interaction between the code snippet and description at the bottom layer of the model during training. To improve the model's effectiveness while preserving its efficiency, we propose a framework, which adopts Self-AdaPtive Model Distillation for Efficient CodE Retrieval, named SPENCER. SPENCER first adopts the dual-encoder to narrow the search space and then adopts the cross-encoder to improve accuracy. To improve the efficiency of SPENCER, we propose a novel model distillation technique, which can greatly reduce the inference time of the dual-encoder while maintaining the overall performance. We also propose a teaching assistant selection strategy for our model distillation, which can adaptively select the suitable teaching assistant models for different pre-trained models during the model distillation to ensure the model performance. Extensive experiments demonstrate that the combination of dual-encoder and cross-encoder improves overall performance compared to solely dual-encoder-based models for code retrieval. Besides, our model distillation technique retains over 98% of the overall performance while reducing the inference time of the dual-encoder by 70%.

Related papers

• CoVAE: Consistency Training of Variational Autoencoders [9.358185536754537]
  We propose a novel single-stage generative autoencoding framework that adopts techniques from consistency models to train a VAE architecture.<n>We show that CoVAE can generate high-quality samples in one or few steps without the use of a learned prior.<n>Our approach provides a unified framework for autoencoding and diffusion-style generative modeling and provides a viable route for one-step generative high-performance autoencoding.
  arXiv  Detail & Related papers  (2025-07-12T01:32:08Z)
• UCD: Unlearning in LLMs via Contrastive Decoding [10.901118996654171]
  We propose an inference-time unlearning algorithm that uses contrastive decoding.<n>We evaluate our approach on two unlearning benchmarks, TOFU and MUSE.
  arXiv  Detail & Related papers  (2025-06-12T16:02:26Z)
• MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings [2.1262605464247812]
  Self-Distillation is a principled approach to trading inference cost for accuracy across various code understanding tasks.<n>Our architecture improves text-to-code and code-to-code search by targeting specific encoder layers as exit heads.<n>We release a new dataset created through code translation that extends text-to-code benchmarks with cross-language code-to-code pairs.
  arXiv  Detail & Related papers  (2025-03-04T21:08:17Z)
• 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)
• Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition [20.052245837954175]
  We propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We introduce an activation caching mechanism to enable the non-autoregressive encoder to operate autoregressively during inference. A hybrid CTC/RNNT architecture which utilizes a shared encoder with both a CTC and RNNT decoder to boost the accuracy and save computation.
  arXiv  Detail & Related papers  (2023-12-27T21:04:26Z)
• Co-training and Co-distillation for Quality Improvement and Compression of Language Models [88.94539115180919]
  Knowledge Distillation (KD) compresses expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models. Most smaller models fail to surpass the performance of the original larger model, resulting in sacrificing performance to improve inference speed. We propose Co-Training and Co-Distillation (CTCD), a novel framework that improves performance and inference speed together by co-training two models.
  arXiv  Detail & Related papers  (2023-11-06T03:29:00Z)
• Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
  In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
  arXiv  Detail & Related papers  (2023-07-17T07:12:29Z)
• Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors [117.61449210940955]
  We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. We introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects. We generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames.
  arXiv  Detail & Related papers  (2023-06-21T06:18:05Z)
• LegoNet: A Fast and Exact Unlearning Architecture [59.49058450583149]
  Machine unlearning aims to erase the impact of specific training samples upon deleted requests from a trained model. We present a novel network, namely textitLegoNet, which adopts the framework of fixed encoder + multiple adapters'' We show that LegoNet accomplishes fast and exact unlearning while maintaining acceptable performance, synthetically outperforming unlearning baselines.
  arXiv  Detail & Related papers  (2022-10-28T09:53:05Z)
• Distilled Dual-Encoder Model for Vision-Language Understanding [50.42062182895373]
  We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks. We show that applying the cross-modal attention distillation for both pre-training and fine-tuning stages achieves further improvements.
  arXiv  Detail & Related papers  (2021-12-16T09:21:18Z)
• Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning [27.04857039060308]
  We propose to combine the best of both worlds to build a retrieval system. We employ a fast bi-encoder to replace the traditional feature-based pre-retrieval model. We train the pre-retrieval model and the re-ranking model at the same time via mutual learning.
  arXiv  Detail & Related papers  (2021-10-01T01:32:33Z)

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.