Tabular data embeddings have become a cornerstone of data profiling and integration pipelines, enabling tasks such as entity annotation, schema matching, column type detection, and table search. Existing approaches embed rows, columns, or entire tables into a vector space and rely on nearest-neighbor search to retrieve candidate matches. A fundamental limitation of current embedding methods is the lack of interpretable similarity scores: the concrete similarity value between a query and its nearest neighbor carries no intrinsic meaning, making it impossible to determine whether that neighbor is a true match or simply the least-dissimilar item in a corpus that contains no valid answer. This inability to set principled thresholds for retrieval undermines practical deployment, particularly for zero-match detection.
We investigate the use of HyperDimensional Computing (HDC), specifically the Holographic Reduced Representations (HRR) model, as a framework for tabular row embeddings when the retrieval task corresponds to answering structured select-project queries in vector space. Exploiting the algebraic properties of HDC operations, we derive closed-form expected similarity values for both equality and non-equality retrieval predicates, which converge to interpretable values as dimensionality increases, and use these to identify suitable retrieval thresholds.
We evaluate HDC against EmbDI, a graph-based baseline, on two real-world datasets across varying table sizes and predicate lengths. Our results show that HDC matches or outperforms EmbDI for row retrieval across all configurations, handles non-equality predicates more robustly, and achieves perfect attribute projection accuracy at sufficient dimensionality—while uniquely enabling reliable identification of zero-match predicates through its principled thresholds.
Blogger's Review: This paper introduces a novel approach using hyperdimensional computing to tackle the interpretability issue of similarity scores in tabular data embeddings, enhancing the reliability and accuracy of querying. This research opens new possibilities in the data retrieval field, making it a significant contribution worth further exploration.