DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation
We design, implement, and evaluate DeepEverest, a system for the efficient execution of interpretation by example queries over the activation values of a deep neural network. DeepEverest consists of an efficient indexing technique and a query execution algorithm with various optimizations. We prove that the proposed query execution algorithm is instance optimal. Experiments with our prototype show that DeepEverest, using less than 20% of the storage of full materialization, significantly accelerates individual queries by up to 63x and consistently outperforms other methods on multi-query workloads that simulate DNN interpretation processes.
Code (1)
Tasks
Network InterpretationSimilar Papers 제목 키워드 기반
Declarative Privacy-Preserving Inference Queries
Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackle this problem, we propose an end-to-end…
Federated LearningManagementPrivacy PreservingDeclarative Design of Neural Predicates in Neuro-Symbolic Systems
Neuro-symbolic systems (NeSy), which claim to combine the best of both learning and reasoning capabilities of artificial intelligence, are missing a core property of reasoning systems: Declarativeness. The lack of declar…
Declarative Sequential Pattern Mining of Care Pathways
Sequential pattern mining algorithms are widely used to explore care pathways database, but they generate a deluge of patterns, mostly redundant or useless. Clinicians need tools to express complex mining queries in orde…
Sequential Pattern MiningRecursive querying of neural networks via weighted structures
Expressive querying of machine learning models - viewed as a form of intentional data - enables their verification and interpretation using declarative languages, thereby making learned representations of data more acces…
Answer Set Programming Modulo `Space-Time'
We present ASP Modulo `Space-Time', a declarative representational and computational framework to perform commonsense reasoning about regions with both spatial and temporal components. Supported are capabilities for mixe…