aws sagemaker

Medical AI deployment is hindered by insufficient production readiness of machine learning (ML) training pipelines. Method: This paper presents a progressive architectural evolution path—monolithic (chaotic) → modular monolithic → microservices—using SPIRA, a voice-based pre-diagnostic system for respiratory insufficiency, as a case study. It systematically introduces continuous training (CT) and a software-quality-attribute-driven MLOps governance framework tailored to healthcare, integrating modular design, microservice decomposition, and engineered CI/CD pipelines. Contribution/Results: The approach significantly improves pipeline maintainability, fault tolerance, and scalability, enabling stable, iterative evolution of SPIRA. It establishes an “agile ML + robust software engineering” co-design paradigm, delivering a reusable methodology and practical benchmark for engineering medical AI in highly regulated environments.

Small- and medium-sized enterprises (SMEs) face prohibitive costs, high production downtime risks, and operational complexity when integrating machine learning (ML) into legacy industrial systems. Method: This paper proposes a human-in-the-loop interactive ML framework that decouples the ML model lifecycle from the production environment via an API-based middleware layer. It employs a lightweight model-serving architecture and a browser-based interactive interface, enabling zero-hardware-upgrade deployment, zero-downtime integration, and remote real-time parameter tuning. Contribution/Results: The framework is the first to support dynamic model maintenance and online collaborative decision-making by domain experts—without modifying existing systems. Experimental evaluation demonstrates substantial reductions in ML adoption barriers and implementation costs, alongside measurable improvements in manufacturing quality and safety. The solution exhibits strong scalability and engineering practicality for industrial deployment.

Machine learning teams face significant challenges in multi-workflow concurrent environments, including redundant intermediate data storage, inefficient cross-pipeline sharing, and high collaboration overhead. To address these issues, this paper proposes and implements a data virtualization service architecture tailored for ML workflows. The architecture adopts a service-oriented design, integrating distributed data management with dynamic metadata mapping to enable logical abstraction, on-demand loading, and unified access to heterogeneous intermediate data. Compared to conventional materialized storage approaches, it reduces storage overhead by an average of 62% (measured empirically) and substantially decreases inter-team collaboration latency. The system has been deployed in production, stably supporting six ML applications and over thirty concurrent workflows, demonstrating linear scalability. This work establishes a lightweight, elastic, and reusable data virtualization paradigm for large-scale ML infrastructure.

Traditional Lean Inception and similar ideation methods lack structured support for ML-specific concerns—namely data dependencies, technical feasibility, and alignment between business objectives and probabilistic system behavior—leading to vision drift and misaligned expectations. Method: We propose Define-ML, an extension of Lean Inception incorporating three novel activities: data source mapping, feature–data source mapping, and ML mapping. This explicitly embeds data constraints and model capabilities into early product ideation. The framework was developed and validated via the Technology Transfer Model, using both a controlled toy problem (static) and an industrial case study (dynamic), supplemented by surveys and expert interviews. Contribution/Results: Define-ML significantly improves cross-functional alignment, clarifies data bottlenecks, and reduces ideation ambiguity. All participants confirmed willingness to adopt it; expert facilitation effectively mitigates implementation barriers.

To address inefficiencies in model incremental updates, unfair policy evaluation, and high retraining costs under continual data growth, this paper proposes an end-to-end adaptive machine learning platform. Methodologically: (1) it introduces a declarative domain-specific language (DSL) to uniformly model data selection strategies (e.g., coreset, uncertainty sampling) and trigger policies (e.g., drift-aware scheduling); (2) it establishes the first composite model evaluation framework enabling fair, cross-policy comparison; and (3) it implements a co-optimization mechanism integrating sample-level fine-grained data selection with high-throughput training. Contributions include an open-source, extensible system architecture, a standardized benchmark ecosystem, and abstracted ML pipeline interfaces. Experiments demonstrate significant improvements in training throughput and substantial reductions in retraining overhead—while preserving model accuracy—and enable reproducible analysis across diverse strategy combinations.

This work addresses the limitations of existing machine learning prototyping tools, which often lack effective support for collaboration and cross-project knowledge reuse, leading to tool fragmentation and insufficient stakeholder engagement. To overcome these challenges, the authors propose Proto-ML, an integrated development environment that unifies prototype implementation, quality evaluation, and knowledge management into three cohesive modules within a single framework. Proto-ML enables structured documentation, multi-role collaboration, and the generation of reusable artifacts. User studies demonstrate that Proto-ML significantly enhances development efficiency while fostering a more transparent and reproducible machine learning development workflow.

This work addresses customs clearance delays in global trade caused by ambiguous product descriptions and frequent updates to Harmonized System (HS) codes. To tackle this challenge, the authors propose a serverless MLOps framework that leverages event-driven pipelines and managed services to enable end-to-end, model-agnostic machine learning lifecycle management. The architecture supports automatic scaling, reproducible training, auditable deployment, and automated A/B testing, ensuring secure and seamless model transitions. By integrating custom text embeddings with models such as Text-CNN, the system achieves 98% accuracy on real-world HS code prediction tasks, meeting stringent service-level agreement (SLA) requirements. This approach significantly reduces long-term operational costs and establishes an efficient, cost-effective, and reproducible deployment paradigm for industrial-scale machine learning systems.

This work proposes the first end-to-end automated artificial intelligence research framework capable of fully automating the development pipeline from algorithmic idea generation to executable machine learning classifiers. The approach integrates structured meta-prompt engineering with large language model–based code generation, augmented by an automated evaluation and iterative optimization mechanism. Experimental results on twenty standard datasets from the Infinity-Bench benchmark demonstrate that multiple novel classifiers autonomously generated by the framework significantly outperform baseline methods implemented in scikit-learn. This study thus achieves, for the first time, complete automation of the entire workflow—from initial algorithmic conception to deployable, runnable code—marking a significant step toward self-driving AI research systems.

Environmental drift renders a substantial number of machine learning notebooks irreproducible, hindering scientific reuse and progress. This work proposes MLEModernizer, a novel framework that leverages large language model (LLM)-driven agents to modernize notebooks without relying on environment rollback. Treating the current execution environment as a fixed constraint, the framework iteratively applies three strategies—error repair, runtime optimization, and score calibration—guided by execution feedback. Evaluated on 7,402 irreproducible notebooks, MLEModernizer successfully restores reproducibility in 5,492 cases (74.2%), significantly enhancing the sustainable usability of machine learning engineering assets.

This work addresses the inefficiencies in large-scale recommendation systems caused by maintaining separate models for different scenarios and objectives, which hinders development velocity and delays technology adoption. To overcome this, the authors propose the Standardized Model Template (SMT) framework, which leverages composable, standardized machine learning components to enable “design once, deploy everywhere,” uniformly accommodating diverse data distributions and optimization objectives. By decoupling model architecture from scenario-specific configurations, SMT reduces the complexity of technology deployment from O(n·2ᵏ) to O(n+k), breaking away from the conventional “one objective, one model” paradigm. Empirical evaluation on Meta’s ad ranking system demonstrates that SMT improves average cross-entropy by 0.63%, reduces engineering time per model iteration by 92%, and increases the throughput of technology-model pair adoption by 6.3×.