Abstract

Modern data-driven applications increasingly rely on distributed graph databases and machine learning pipelines to extract knowledge from massive datasets. However, efficient query processing in distributed environments remains challeng-ing due to issues such as graph partitioning inefficiencies, dynamic connectivity updates, privacy constraints, and suboptimal ranking of query results. Exist- ing systems typically address these issues independently, resulting in fragmented solutions that do not fully optimize query execution, data preparation, and result retrieval simultaneously. This paper proposesCODAQ (Context-Oriented Distributed Adaptive Query Processing), a novel unified framework that integrates connectivity- aware graph partitioning, constant-time dynamic connectivity indexing, context- aware pipeline optimization, directional ranking for balanced top-k results, and disclosure-compliant query rewriting. CODAQ reduces crosspartition communi-cation, dynamically maintains graph connectivity structures, learns optimal data preparation pipelines using contextual embeddings, and ensures secure data dis-closure while maintaining result relevance. Experimental evaluation demonstrates that CODAQ improves query throughput by up to 65%, reduces communica- tion overhead by 70%, and achieves higher accuracy in data-driven applications compared to existing distributed query processing frameworks.