Tabular Learning: Encoding for Entity and Context Embeddings

arXiv:2403.19405v1 Announce Type: new
Abstract: Examining the effect of different encoding techniques on entity and context embeddings, the goal of this work is to challenge commonly used Ordinal encoding for tabular learning. Applying different preprocessing methods and network architectures over several datasets resulted in a benchmark on how the encoders influence the learning outcome of the networks. By keeping the test, validation and training data consistent, results have shown that ordinal encoding is not the most suited encoder for categorical …

abstract architectures arxiv benchmark challenge context cs.ai cs.ce cs.lg datasets embeddings encoding influence network ordinal tabular type work