RowNet: A Memory Transformer for Tabular Regression

• URL: http://arxiv.org/abs/2606.04445v1
• Date: Wed, 03 Jun 2026 04:47:38 GMT
• Title: RowNet: A Memory Transformer for Tabular Regression
• Abstract summary: This paper presents RowNet, a retrieval-based neural architecture for real estate price-per-square-meter prediction.<n>RowNet represents a query property through pairwise similarity features against a memory bank of labeled properties.<n>A second layer augments the memory comparison with target-consistency features and uses multiple learned attention heads to retrieve complementary comparable sets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real estate valuation is a structured regression problem in which prices are governed by heterogeneous feature types, sparse regional effects, nonlinear interactions, and the practical logic of comparable properties. Standard multilayer perceptrons treat each row as an isolated vector and must learn locality, scale sensitivity, and categorical matching from supervision alone. Gradient-boosted decision trees provide strong tabular baselines, but their feature-centric splitting mechanism does not explicitly model the retrieval of similar historical observations. This paper presents RowNet, a retrieval-based neural architecture for real estate price-per-square-meter prediction. RowNet represents a query property through pairwise similarity features against a memory bank of labeled properties. A first retrieval layer estimates a coarse target from feature-only similarities. A second layer augments the memory comparison with target-consistency features and uses multiple learned attention heads to retrieve complementary comparable sets. A final mixture-of-experts module combines learned gating, residual correction, entropy regularization, and head-diversity regularization to produce the prediction.

Related papers

• Handling Missing Data in Probabilistic Regression Trees [0.0]
  This paper extends the PRTree framework to accommodate missing predictor values directly during tree construction.<n>Three strategies are proposed, each exploiting the available information differently.<n>The effectiveness of probabilistic tree construction depends strongly on the treatment of missing observations.
  arXiv  Detail & Related papers  (2026-08-06T15:54:12Z)
• Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing [0.18006769874322107]
  We study how similarity scores can be related by learning mappings between score distributions rather than embeddings.<n>We introduce Synthetic Query Probing, generating queries from documents to create controlled query-chunk pairs.<n>Experiments on SciFact and a proprietary corpus show that while models largely agree on rankings, their absolute scores exhibit systematic distortions.
  arXiv  Detail & Related papers  (2026-08-06T10:38:13Z)
• From Classification to Regression: Using a Fruitfly to Solve Equations [0.5729426778193397]
  We formulate a general framework for learning nonlinear input-output relationships.<n>We generate predictions by measuring similarities between a query and stored patterns.<n>We apply this approach to nonlinear dynamical systems, data-driven regression, and physics-informed learning.
  arXiv  Detail & Related papers  (2026-07-29T17:58:05Z)
• Memory by Design: Probabilistic Sequence Layers [19.16406809753255]
  We introduce a way to derive efficient recurrent sequence maps from explicit assumptions about memory.<n>A design model writes evidence into memory by exact Bayesian filtering.<n>A query-dependent readout produces a predictive distribution whose mean is the layer output.
  arXiv  Detail & Related papers  (2026-05-29T11:13:00Z)
• Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories [7.048738972394742]
  This work presents the first explicit evaluation for the robustness of the attribute prediction task under such conditions.<n>We introduce train-test split strategies that progressively reduce correlation between training and test sets.<n>Results show a sharp drop in performance as the correlation between training and test categories decreases.
  arXiv  Detail & Related papers  (2025-09-04T17:52:22Z)
• Structured Radial Basis Function Network: Modelling Diversity for Multiple Hypotheses Prediction [51.82628081279621]
  Multi-modal regression is important in forecasting nonstationary processes or with a complex mixture of distributions. A Structured Radial Basis Function Network is presented as an ensemble of multiple hypotheses predictors for regression problems. It is proved that this structured model can efficiently interpolate this tessellation and approximate the multiple hypotheses target distribution.
  arXiv  Detail & Related papers  (2023-09-02T01:27:53Z)
• Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction [52.63663547523033]
  Late interaction, the simplest form of multi-vector, is also helpful to neural rerankers that only use the [] vector to compute the similarity score. We show that the finding is consistent across different model sizes and first-stage retrievers of diverse natures.
  arXiv  Detail & Related papers  (2023-02-13T18:42:17Z)
• Distributional Adaptive Soft Regression Trees [0.0]
  This article proposes a new type of a distributional regression tree using a multivariate soft split rule. One great advantage of the soft split is that smooth high-dimensional functions can be estimated with only one tree. We show by means of extensive simulation studies that the algorithm has excellent properties and outperforms various benchmark methods.
  arXiv  Detail & Related papers  (2022-10-19T08:59:02Z)
• Semantic Self-adaptation: Enhancing Generalization with a Single Sample [45.111358665370524]
  We propose a self-adaptive approach for semantic segmentation. It fine-tunes the parameters of convolutional layers to the input image using consistency regularization. Our empirical study suggests that self-adaptation may complement the established practice of model regularization at training time.
  arXiv  Detail & Related papers  (2022-08-10T12:29:01Z)
• Harmless interpolation in regression and classification with structured features [21.064512161584872]
  Overparametrized neural networks tend to perfectly fit noisy training data yet generalize well on test data. We present a general and flexible framework for upper bounding regression and classification risk in a reproducing kernel Hilbert space.
  arXiv  Detail & Related papers  (2021-11-09T15:12:26Z)
• Intersection Regularization for Extracting Semantic Attributes [72.53481390411173]
  We consider the problem of supervised classification, such that the features that the network extracts match an unseen set of semantic attributes. For example, when learning to classify images of birds into species, we would like to observe the emergence of features that zoologists use to classify birds. We propose training a neural network with discrete top-level activations, which is followed by a multi-layered perceptron (MLP) and a parallel decision tree.
  arXiv  Detail & Related papers  (2021-03-22T14:32:44Z)
• AttriMeter: An Attribute-guided Metric Interpreter for Person Re-Identification [100.3112429685558]
  Person ReID systems only provide a distance or similarity when matching two persons. We propose an Attribute-guided Metric Interpreter, named AttriMeter, to semantically and quantitatively explain the results of CNN-based ReID models.
  arXiv  Detail & Related papers  (2021-03-02T03:37:48Z)
• FREEtree: A Tree-based Approach for High Dimensional Longitudinal Data With Correlated Features [2.00191482700544]
  FREEtree is a tree-based method for high dimensional longitudinal data with correlated features. It exploits the network structure of the features by first clustering them using weighted correlation network analysis. It then conducts a screening step within each cluster of features and a selection step among the surviving features.
  arXiv  Detail & Related papers  (2020-06-17T07:28:11Z)
• Nonparametric Score Estimators [49.42469547970041]
  Estimating the score from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models. We provide a unifying view of these estimators under the framework of regularized nonparametric regression. We propose score estimators based on iterative regularization that enjoy computational benefits from curl-free kernels and fast convergence.
  arXiv  Detail & Related papers  (2020-05-20T15:01:03Z)
• Learning from Aggregate Observations [82.44304647051243]
  We study the problem of learning from aggregate observations where supervision signals are given to sets of instances. We present a general probabilistic framework that accommodates a variety of aggregate observations. Simple maximum likelihood solutions can be applied to various differentiable models.
  arXiv  Detail & Related papers  (2020-04-14T06:18:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.