Trustworthy Tree-based Machine Learning by $MoS_2$ Flash-based Analog CAM with Inherent Soft Boundaries

2025-07-16

AI Summary

Hardware acceleration of tree-based models (e.g., Random Forest, XGBoost) suffers from poor robustness, vulnerability to device variations and adversarial attacks, and limited interpretability—largely due to hard decision boundaries inherent in digital implementations. Method: This work proposes an in-memory computing architecture based on molybdenum disulfide (MoS₂) flash memory, implementing soft-boundary analog content-addressable memory (CAM). Leveraging the intrinsic analog characteristics of MoS₂ devices, it realizes hardware-efficient soft decision boundaries and establishes a hardware-algorithm co-designed soft decision tree inference paradigm that is both interpretable and robust. Contribution/Results: The architecture achieves 96% accuracy on the WDBC dataset. Under 10% threshold variation, MNIST accuracy degrades by only 0.6%, outperforming conventional approaches—whose accuracy drops by 45.3% under identical conditions. The design simultaneously delivers high energy efficiency, enhanced trustworthiness, and model interpretability.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Analogy
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance

Abstract

The rapid advancement of artificial intelligence has raised concerns regarding its trustworthiness, especially in terms of interpretability and robustness. Tree-based models like Random Forest and XGBoost excel in interpretability and accuracy for tabular data, but scaling them remains computationally expensive due to poor data locality and high data dependence. Previous efforts to accelerate these models with analog content addressable memory (CAM) have struggled, due to the fact that the difficult-to-implement sharp decision boundaries are highly susceptible to device variations, which leads to poor hardware performance and vulnerability to adversarial attacks. This work presents a novel hardware-software co-design approach using $MoS_2$ Flash-based analog CAM with inherent soft boundaries, enabling efficient inference with soft tree-based models. Our soft tree model inference experiments on $MoS_2$ analog CAM arrays show this method achieves exceptional robustness against device variation and adversarial attacks while achieving state-of-the-art accuracy. Specifically, our fabricated analog CAM arrays achieve $96%$ accuracy on Wisconsin Diagnostic Breast Cancer (WDBC) database, while maintaining decision explainability. Our experimentally calibrated model validated only a $0.6%$ accuracy drop on the MNIST dataset under $10%$ device threshold variation, compared to a $45.3%$ drop for traditional decision trees. This work paves the way for specialized hardware that enhances AI's trustworthiness and efficiency.

Problem

• Enhancing AI trustworthiness via interpretable tree-based models
• Overcoming computational cost in scaling tree-based ML models
• Addressing device variation vulnerability in analog CAM hardware

Innovation

• Uses $MoS_2$ Flash-based analog CAM
• Implements soft tree-based models
• Enhances robustness against device variations