{"ID":2855833,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12659","arxiv_id":"2510.12659","title":"SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning","abstract":"We propose SG-XDEAT (Sparsity-Guided Cross Dimensional and Cross-Encoding Attention with Target Aware Conditioning), a novel framework designed for supervised learning on tabular data. At its core, SG-XDEAT employs a dual-stream encoder that decomposes each input feature into two parallel representations: a raw value stream and a target-conditioned (label-aware) stream. These dual representations are then propagated through a hierarchical stack of attention-based modules. SG-XDEAT integrates three key components: (i) Cross-Dimensional self-attention, which captures intra-view dependencies among features within each stream; (ii) Cross-Encoding self-attention, which enables bidirectional interaction between raw and target-aware representations; and (iii) an Adaptive Sparse Self-Attention (ASSA) mechanism, which dynamically suppresses low-utility tokens by driving their attention weights toward zero--thereby mitigating the impact of noise. Empirical results on multiple public benchmarks show consistent gains over strong baselines, confirming that jointly modeling raw and target-aware views--while adaptively filtering noise--yields a more robust deep tabular learner.","short_abstract":"We propose SG-XDEAT (Sparsity-Guided Cross Dimensional and Cross-Encoding Attention with Target Aware Conditioning), a novel framework designed for supervised learning on tabular data. At its core, SG-XDEAT employs a dual-stream encoder that decomposes each input feature into two parallel representations: a raw value s...","url_abs":"https://arxiv.org/abs/2510.12659","url_pdf":"https://arxiv.org/pdf/2510.12659v1","authors":"[\"Chih-Chuan Cheng\",\"Yi-Ju Tseng\"]","published":"2025-10-14T15:56:40Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}