Feature Interaction Modeling

Overview

Feature interaction modeling studies how the effect of one input depends on other inputs, allowing models to capture combinations that additive methods miss. It matters in settings such as recommendation, tabular prediction, forecasting, and scientific data analysis, where useful signals may arise from feature combinations rather than individual variables. Common approaches include multiplicative or tensor-based interactions, attention and token mixing, selective interaction layers, and interpretable decompositions using GAMs, ANOVA, or Shapley methods. A central tension is how to recover meaningful higher-order structure without introducing spurious interactions, excessive computation, or explanations that fail under correlated or limited data.

Latest papers

CardsList

78 papers11 papers in the last four weeks, up 10% on the four weeks before. 0.1% of all new papers.

  1. TokenFormer V2: Breaking the Resolution-Complexity Dilemma in Unified Recommendation

    Nov 14, 2026Kaihui Wu, Guoming Li, Liang Guo +8Recommender SystemsFeature Interaction Modeling

  2. Learning nonlinear interactions and cross-feature couplings with product-unit residual networks

    Nov 13, 2026Ziyuan Li, Uwe Jaekel, Babette DellenFeature Interaction ModelingNeural Network Interpretability

  3. Do Feature Interactions Break Explainability? Provable Explanations for Any-Order Neural Additive Models

    Nov 8, 2026Idan Refaeli, Yizhak Yisrael Elboher, Guy Katz +1Neural Network InterpretabilityFeature Interaction Modeling

  4. An Interaction-Aware Decision Framework for FDIC-Assisted Distressed Bank Acquisitions: Empirical Evidence from the FDIC Failed-Bank Panel and the SVB-First Citizens Case

    Nov 4, 2026Yousef Nejatbakhsh, Malihe Aliasgari, Parsa Safaee +1FinanceFinancial Decision-Making

  5. InterFuse: Interaction-Guided Adaptive Fusion of Heterogeneous Models for Payment Risk Ranking

    Nov 2, 2026Haoyu Jiang, Weiyu Han, Ze Zhao +5Rank AggregationMulti-View Feature Fusion

  6. Hierarchical Multimodal Interaction Reasoning for Dyadic Relationship Recognition

    Oct 26, 2026Wang Tang, Fethiye Irmak Dogan, Linbo Qing +2Relational ReasoningMultimodal Reasoning

  7. EASformer: Environment-Action-State Alignment for Industrial Generative Ranking

    Oct 20, 2026Bohao Li, DingLun Cao, Pengcheng Huang +11Learning to RankGenerative Recommendation

  8. Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection

    Oct 19, 2026Mosh Levy, Aly Lidayan, Yoav GoldbergJoint-Embedding Predictive ArchitecturePredictive Representation Learning

  9. A Multi-granularity Interaction Network for Relational Triple Extraction

    Oct 18, 2026Xiaocheng Luo, Yanping Chen, Zaifu ZhanRelation ExtractionFeature Interaction Modeling

  10. Behavioral Compositionality of Sparse Autoencoder Representations

    Oct 15, 2026Haotian Ma, Ziye Mei, Frederic SalaSparse AutoencodersCompositional Representation Learning

  11. Graph Additive Models disentangling feature, topology, and interactions

    Oct 14, 2026Clara Alvarez-Rodriguez, Steve Azzolin, Vincenzo Marco De Luca +3Graph Neural NetworksGNN Explainability

  12. Better Capturing Interactions Between Products inRetail: Revisited Negative Sampling forBasket Choice Modeling

    Oct 13, 2026Jules Désir, Vincent Auriau, Martin Možina +1Discrete Choice ModelingFeature Interaction Modeling

  13. RelICL: Training-free Relational Learning with Tabular Foundation Models

    Oct 1, 2026Simon Forbat, Rainer GemullaTabular Foundation ModelsFeature Interaction Modeling

  14. Beyond Interaction Capacity: Estimator Scaling with Recursive Models for CTR Prediction

    Sep 29, 2026Shivang Chopra, Fotis Iliopoulos, Zsolt Kira +1Feature Interaction ModelingEnsemble Learning

  15. Correction-space Cross-variate Interaction for Test-time Adaptation in Time Series Forecasting

    Sep 28, 2026Yuanyuan Deng, Mykola Pechenizkiy, Songgaojun DengMultivariate Time Series ForecastingFeature Interaction Modeling

  16. When Does Synergy Help Active Feature Acquisition? A PID-Based Study

    Sep 26, 2026Jie Li, Maruf A. Dhali, Hjalmar R. BoumaActive Feature AcquisitionFeature Interaction Modeling

  17. QueryFormer: Winning Solution for KDD Cup 2026 Tencent UniRec Challenge

    Sep 15, 2026Yuanzhe Zhou, Zhaoyang ZengConversion Rate PredictionUser Modeling

  18. Typed Temporal Interaction Features for Simulation-Backed Forecasting of Open-Source Game Release Incidents

    Sep 12, 2026Shayma Alkobaisi, Anas AliFeature Interaction Modeling

  19. Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding

    Sep 8, 2026Namwoo Kim, Jeeyun Chang, Kanghoon Lee +1Feature Interaction ModelingGeospatial Representation Learning

  20. Temporal Heterogeneous Graph Transformer for Credit Card Fraud Detection

    Sep 7, 2026Qinwen YanFinancial Fraud DetectionTransformer

  21. Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction

    Sep 6, 2026Wei Sun, Tingyu Qu, Jesse Davis +1Relation ExtractionFeature Interaction Modeling

  22. From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models

    Aug 31, 2026Zichen Luo, Jiachen Guo, Keming Gu +1Recommender SystemsFeature Interaction Modeling

  23. Advancing Interaction-Sensitive Feature Selection: Novel Relief-Based Algorithms, Expanded Comparisons, and Recommendations for Biomedical Data Mining

    Aug 28, 2026Kia Kazemi-Nia, Harsh Bandhey, Philip J. Freda +1Feature SelectionFeature Interaction Modeling

  24. When Similarity Is Interaction-Driven: Quantum Kernels for Regime-Sensitive Learning

    Aug 25, 2026Hanqiu Peng, Jianlong Lu, Ying ChenQuantum Feature MapsFeature Interaction Modeling