[
    {
        "id": "osp-15295",
        "type": "article-journal",
        "title": "QCATS: Query Context-Aware Transformer Slicing for Efficient Predictive Query Processing",
        "author": [
            {
                "family": "Li",
                "given": "Yueying"
            },
            {
                "family": "Xie",
                "given": "Zhongle"
            },
            {
                "family": "Chen",
                "given": "Ke"
            },
            {
                "family": "Shou",
                "given": "Lidan"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/qcats-query-context-aware-transformer-slicing-for-efficient-predictive-query-processing",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "In-database predictive query processing increasingly applies Transformer-based models within relational pipelines. However, existing in-database inference typically exposes only tuple-level model inputs to the inference runtime, leaving relational predicates and metadata statistics invisible to neural execution planning. In this paper, we propose QCATS, a query context-aware transformer slicing framework that enables efficient sparse inference inside database systems. QCATS executes at query granularity: instead of routing individual tokens or tuples during inference, it uses query predicates and metadata statistics to pre-select context-aligned FFN slices before model execution. The framework comprises offline expert construction and lightweight query-level routing that dynamically selects experts during execution. QCATS further introduces system optimizations, including asynchronous CPU-GPU pipelines and routing-aware batching. Experiments on four predictive-query workloads with BERT-base and Qwen-0.6B show that QCATS achieves up to 4.42x latency reduction while preserving prediction accuracy comparable to dense baselines."
    }
]