CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces
2026-05-22 • Databases
DatabasesArtificial IntelligenceCryptography and SecurityMachine LearningMultiagent Systems
AI summaryⓘ
The authors address problems in data marketplaces for changing temporal knowledge graphs, where static designs struggle with outdated shortcuts, inaccurate value pricing, and privacy budget misuse. They propose CHRONOS, a three-layer system that improves recall with neural-ODE decay, adjusts pricing based on change detection, and carefully manages privacy using an advanced bandit algorithm. Their approach releases privatized data safely while maintaining efficient retrieval and fair valuation over time. Tests show CHRONOS balances accuracy, speed, and privacy well, though valuations remain noisy due to strict privacy constraints.
temporal knowledge graphdata marketplaceneural-ODEShapley valuedifferential privacyEXP3-IX algorithmGaussian mechanismrecallprivacy budgetchange point detection
Authors
Joydeep Chandra
Abstract
Temporal knowledge-graph data marketplaces face three coupled failures in static designs: stale hybrid index shortcuts reduce recall as edges evolve, stationary Shapley pricing misattributes value after distribution shifts, and uncoordinated agents over-consume a shared differential-privacy budget. We present CHRONOS, a three-layer architecture providing a unified treatment of these challenges with explicit public and private separation. Layer one applies neural-ODE temporal decay to shortcut edges, providing a per-query expected recall-loss bound of Big-O of Pq lambda delta t, with a monotone-envelope guarantee reducing bound looseness to 1.8 to 3.2 times observed loss. Layer two conditions Shapley valuation on detected changepoints and provides finite-sample error guarantees under noise. Layer three uses EXP3-IX to achieve Big-O of the square root of T log T regret while enforcing epsilon and delta differential privacy via moments accounting. CHRONOS releases a privatized affinity matrix per epoch using the Gaussian mechanism; all retrieval and ranking are post-processing, incurring no extra privacy cost. We provide multi-epoch settlement, scalability analysis for 500 sellers, and comparisons against accelerated baselines. Across four benchmarks, CHRONOS shows 0.937 recall at ten, 2.74 queries per second, 161 ms latency, and total epsilon of 4.25 at delta of 10 to the power of negative 6 under zCDP composition. These results indicate a competitive operating point. A limitation is that at this privacy level, released valuations remain noise-dominated; utility derives primarily from public index routing and adaptive scheduling driven by low-sensitivity statistics.