LGAIMay 25, 2022

NECA: Network-Embedded Deep Representation Learning for Categorical Data

arXiv:2205.12752v1h-index: 18
Originality Synthesis-oriented
AI Analysis

This addresses the challenge of handling categorical data in data mining, though it appears incremental as it builds on existing network embedding and deep learning techniques.

The paper tackles the problem of learning representations for categorical data by proposing NECA, a method that embeds attribute relationships into numeric vectors, and shows it effectively supports downstream tasks like clustering.

We propose NECA, a deep representation learning method for categorical data. Built upon the foundations of network embedding and deep unsupervised representation learning, NECA deeply embeds the intrinsic relationship among attribute values and explicitly expresses data objects with numeric vector representations. Designed specifically for categorical data, NECA can support important downstream data mining tasks, such as clustering. Extensive experimental analysis demonstrated the effectiveness of NECA.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes