0 views collected around this technical thread.
This article presents a self‑isolation based streaming anomaly detection framework that combines memory‑space indexing to capture pattern anomalies, long‑term memory, and concept drift in time‑series data, and validates the approach with public benchmarks and real‑world risk‑control scenarios.
This article introduces the HG‑LDP framework, which combines local differential privacy with the HeavyGuardian data structure to enable accurate, privacy‑preserving high‑frequency item statistics on streaming data while using only limited memory, and evaluates four algorithmic variants (BGR, DSR, BDR, CNR) through extensive experiments on synthetic and real‑world datasets.
The paper introduces SGNN‑GR, a framework that pairs a graph neural network with a GAN‑based generative model to replay synthetic historical nodes, enabling continual learning on evolving graphs without storing raw data, achieving near‑retraining accuracy while being 3–6× faster per iteration.
The article details Alibaba’s end‑to‑end online‑learning pipeline for real‑time ranking in the Taobao home‑decor channel, covering UT log parsing, full‑feature extraction, ODL sample creation, xDeepCTR model training, and deployment, which yielded up to 7.8% CTR improvement and demonstrates the value of rapid model adaptation.
The talk by Zha Jia showcases StreamNative’s open‑source Function Mesh, which builds on Apache Pulsar’s unified messaging and streaming platform and its lightweight Pulsar Functions, using Kubernetes CRDs to simplify deployment, management, and scaling of serverless data processing while highlighting the project’s rapid community growth.
This article presents an in‑depth overview of Beike's four‑layer streaming data platform, covering the foundational infrastructure, capability aggregation, data content, and output layers, as well as the challenges of metadata management, real‑time processing, and productization through the Ark and Tianyan systems.