# SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval

arXiv: https://arxiv.org/abs/2508.00546 · HTML: https://mlsanity.com/paper/2508.00546/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 66 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Builds on (most cited first, 30 of 46)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Distilling Task-Specific Knowledge from BERT into Simple Neural Networks](https://mlsanity.com/paper/1903.12136/) (2019)
- [Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants](https://mlsanity.com/paper/2208.09727/) (2022)
- [Densely Guided Knowledge Distillation using Multiple Teacher Assistants](https://mlsanity.com/paper/2009.08825/) (2020)
- [Contrastive Code Representation Learning](https://mlsanity.com/paper/2007.04973/) (2020)
- [SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation](https://mlsanity.com/paper/2108.04556/) (2021)
- [Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System](https://mlsanity.com/paper/1809.07428/) (2018)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)

## Built on by (most cited first, 5 of 5)

- [AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion](https://mlsanity.com/paper/2601.19697/) (2026)
- [SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion](https://mlsanity.com/paper/2510.17925/) (2025)
- [DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning](https://mlsanity.com/paper/2601.20615/) (2026)
- [PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents](https://mlsanity.com/paper/2607.18859/) (2026)
- [XSearch: Explainable Code Search via Concept-to-Code Alignment](https://mlsanity.com/paper/2605.16046/) (2026)

## Abstract (arXiv)

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%.