mlsanityData to 14 Oct 2026

Search-Optimized Quantization in Biomedical Ontology Alignment

arXiv 2507.13742 ↗First posted 18 Jul 2025cs.LG cs.AI math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

In the fast-moving world of AI, as organizations and researchers develop more advanced models, they face challenges due to their sheer size and computational demands. Deploying such models on edge devices or in resource-constrained environments adds further challenges related to energy consumption, memory usage and latency. To address these challenges, emerging trends are shaping the future of efficient model optimization techniques. From this premise, by employing supervised state-of-the-art transformer-based models, this research introduces a systematic method for ontology alignment, grounded in cosine-based semantic similarity between a biomedical layman vocabulary and the Unified Medical Language System (UMLS) Metathesaurus. It leverages Microsoft Olive to search for target optimizations among different Execution Providers (EPs) using the ONNX Runtime backend, followed by an assembled process of dynamic quantization employing Intel Neural Compressor and IPEX (Intel Extension for PyTorch). Through our optimization process, we conduct extensive assessments on the two tasks from the DEFT 2020 Evaluation Campaign, achieving a new state-of-the-art in both. We retain performance metrics intact, while attaining an average inference speed-up of 20x and reducing memory usage by approximately 70%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 67 references that are in the map. First posted on arXiv 18 Jul 2025.

Builds on

40 of 67 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  7. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  8. 2017Mixed Precision Trainingcited by 1,156
  9. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
  10. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  11. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  12. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 442
28 more
  1. 2019Q-BERT: Hessian Based Ultra Low Precision Quantization of BERTcited by 359
  2. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 336
  3. 2021Post-Training Quantization for Vision Transformercited by 278
  4. 2021I-BERT: Integer-only BERT Quantizationcited by 255
  5. 2019ScispaCy: Fast and Robust Models for Biomedical Natural Language Processingcited by 244
  6. 2020Self-Alignment Pretraining for Biomedical Entity Representationscited by 237
  7. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  8. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 188
  9. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 151
  10. 2015Compressing Neural Networks with the Hashing Trickcited by 150
  11. 2019Zero-Shot Entity Linking by Reading Entity Descriptionscited by 124
  12. 2020BioMegatron: Larger Biomedical Domain Language Modelcited by 76
  13. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 65
  14. 2020Biomedical Entity Representations with Synonym Marginalizationcited by 61
  15. 2020Differentiable Joint Pruning and Quantization for Hardware Efficiencycited by 46
  16. 2018MedSTS: A Resource for Clinical Semantic Textual Similaritycited by 39
  17. 2021Knowledge-Rich Self-Supervision for Biomedical Entity Linkingcited by 31
  18. 2019BERT-based Ranking for Biomedical Entity Normalizationcited by 30
  19. 2019Adaptive Loss-aware Quantization for Multi-bit Networkscited by 30
  20. 2018Ontology Alignment in the Biomedical Domain Using Entity Definitions and Contextcited by 10
  21. 2023Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantizationcited by 10
  22. 2020Joint Pruning & Quantization for Extremely Sparse Neural Networkscited by 9
  23. 2023Bioformer: an efficient transformer language model for biomedical text miningcited by 9
  24. 2019TiM-DNN: Ternary in-Memory accelerator for Deep Neural Networkscited by 7
  25. 2022Mixed-Precision Neural Networks: A Surveycited by 7
  26. 2017Model compression as constrained optimization, with application to neural nets. Part I: general frameworkcited by 6
  27. 2022On generalization bounds for deep networks based on loss surface implicit regularizationcited by 5
  28. 2023Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantizationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization
  2. 2026Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning
  3. 2025Large Language Models as Oracles for Ontology Alignment
  4. 2025Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation
  5. 2026Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field
  6. 2026OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques
  7. 2023Exploring Large Language Models for Ontology Alignment
  8. 2026HyEm: Query-Adaptive Hyperbolic Retrieval for Biomedical Ontologies via Euclidean Vector Indexing