Paper Reading AI Learner

ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks

2019-07-17 16:58:33
Xuankang Lin, He Zhu, Roopsha Samanta, Suresh Jagannathan

Abstract

Artificial neural networks (ANNs) have demonstrated remarkable utility in a variety of challenging machine learning applications. However, their complex architecture makes asserting any formal guarantees about their behavior difficult. Existing approaches to this problem typically consider verification as a post facto white-box process, one that reasons about the safety of an existing network through exploration of its internal structure, rather than via a methodology that ensures the network is correct-by-construction. In this paper, we present a novel learning framework that takes an important first step towards realizing such a methodology. Our technique enables the construction of provably correct networks with respect to a broad class of safety properties, a capability that goes well-beyond existing approaches. Overcoming the challenge of general safety property enforcement within the network training process in a supervised learning pipeline, however, requires a fundamental shift in how we architect and build ANNs. Our key insight is that we can integrate an optimization-based abstraction refinement loop into the learning process that iteratively splits the input space from which training data is drawn, based on the efficacy with which such a partition enables safety verification. To do so, our approach enables training to take place over an abstraction of a concrete network that operates over dynamically constructed partitions of the input space. We provide theoretical results that show that classical gradient descent methods used to optimize these networks can be seamlessly adopted to this framework to ensure soundness of our approach. Moreover, we empirically demonstrate that realizing soundness does not come at the price of accuracy, giving us a meaningful pathway for building both precise and correct networks.

Abstract (translated)

URL

https://arxiv.org/abs/1907.10662

PDF

https://arxiv.org/pdf/1907.10662.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot