CQELS 2.0: Towards A Unified Framework for Semantic Stream Fusion

TL;DR

CQELS 2.0 introduces a unified, platform-agnostic framework for semantic stream fusion that integrates neural-symbolic reasoning and adaptive federated processing for diverse hardware environments.

Contribution

It presents a novel neural-symbolic reasoning component and an adaptive federator, enabling deep neural network-based data fusion with flexible, distributed execution across heterogeneous devices.

Findings

Neural-symbolic reasoning enables complex data fusion pipelines.

Adaptive federator improves resource coordination across network nodes.

Framework supports diverse hardware architectures from embedded to cloud.

Abstract

We present CQELS 2.0, the second version of Continuous Query Evaluation over Linked Streams. CQELS 2.0 is a platform-agnostic federated execution framework towards semantic stream fusion. In this version, we introduce a novel neural-symbolic stream reasoning component that enables specifying deep neural network (DNN) based data fusion pipelines via logic rules with learnable probabilistic degrees as weights. As a platform-agnostic framework, CQELS 2.0 can be implemented for devices with different hardware architectures (from embedded devices to cloud infrastructures). Moreover, this version also includes an adaptive federator that allows CQELS instances on different nodes in a network to coordinate their resources to distribute processing pipelines by delegating partial workloads to their peers via subscribing continuous queries