"stream processing"

Towards Multimodal Stream Processing Systems

In this paper, we present a vision for a new generation of multimodal streaming systems that embed MLLMs as first-class operators, enabling real-time query processing across multiple modalities. Achieving this is non-trivial: while recent work has …

Learning What Matters: Automated Feature Selection for Learned Cost Model in Parallel Stream Processing

Learned cost models for parallel stream processing typically rely on hand-engineered features, which requires substantial domain expertise and manual effort. This paper presents an automated feature selection pipeline that identifies the features …

Learned Cost Models for Query Optimization: From Batch to Streaming Systems

Learned cost models (LCMs) have recently gained traction as a promising alternative to traditional cost estimation techniques in data management, offering improved accuracy by capturing complex interactions between queries, data, and runtime …

Dema: Efficient Decentralized Aggregation for Non-Decomposable Quantile Functions

The growing number of IoT devices has led to decentralized networks for handling unbounded data streams, but traditional centralized window aggregation results in high network overhead and processing bottlenecks. Current decentralized solutions only …

PDSP-Bench: A Benchmarking System for Parallel and Distributed Stream Processing

PDSP-Bench is a novel benchmarking system designed for a systematic understanding of performance of parallel stream processing in a distributed environment. While existing benchmarking systems focus on analyzing stream processing systems using …

COSTREAM: Learned Cost Models for Operator Placement in Edge-Cloud Environments

COSTREAM provides a learned cost model for Distributed Stream Processing Systems that can accurately predict the execution costs of a streaming query in an edge-cloud environment. The model can be used to find an initial placement of operators across …

ZERoTuNE: Learned Zero-Shot Cost Models for Parallelism Tuning in Stream Processing

ZERoTuNE introduces a novel cost model for parallel and distributed stream processing that can be used to effectively set initial parallelism degrees of streaming queries. Unlike existing models, which rely majorly on online learning statistics that …

Deco: Fast and Accurate Decentralized Aggregation of Count-Based Windows in Large-Scale IoT Applications

Aggregating data using count-based windows is a formidable challenge in large-scale, decentralized IoT networks, where events arrive at varying rates, unordered, and at diverse times. Existing methods are either centralized and slow, or decentralized …

No One Size (PPM) Fits All: Towards Privacy in Stream Processing Systems

Stream processing systems designed to process data streams in real-time must handle sensitive or personal data across multilayered systems (sensor, fog, and cloud layers), which raises privacy concerns as data may be subject to unauthorized access …

Zero-Shot Cost Models for Parallel Stream Processing

This paper presents zero-shot cost models for parallel stream processing, enabling accurate cost predictions for parallel streaming queries without having observed any query deployment. The approach leverages data-efficient zero-shot learning …