Hypernetworks for Dynamic Feature Selection

• URL: http://arxiv.org/abs/2605.12278v1
• Date: Tue, 12 May 2026 15:37:24 GMT
• Title: Hypernetworks for Dynamic Feature Selection
• Abstract summary: Dynamic feature selection (DFS) is a machine learning framework in which features are acquired sequentially for individual samples under budget constraints.<n>In this paper, we study the structural limitations of existing DFS approaches to achieve an optimal solution.<n>We propose textscHyper-DFS, a hypernetwork-based DFS approach that generates feature subset-specific parameters on demand.
• Score: 2.564905016909138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic feature selection (DFS) is a machine learning framework in which features are acquired sequentially for individual samples under budget constraints. The exponential growth in the number of possible feature acquisition paths forces a DFS model to balance fitting specific scenarios against maintaining general performance, even when the feature space is moderate in size. In this paper, we study the structural limitations of existing DFS approaches to achieve an optimal solution. Then, we propose \textsc{Hyper-DFS}, a hypernetwork-based DFS approach that generates feature subset-specific classifier parameters on demand. We show that the use of hypernetworks compared to mask-embedding methods results in a smaller structural complexity bound. We also use a Set Transformer encoding to create a smooth conditioning space for the hypernetwork, so that functionally similar tasks are also geometrically close. In our benchmarks, \textsc{Hyper-DFS} outperforms all state-of-the-art approaches on synthetic and real-life tabular data. It is also competitive or superior across all image datasets tested, and shows substantially stronger zero-shot generalisation to feature subsets never seen during training than existing DFS approaches.

Related papers

• Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery [52.29866804948133]
  We propose CAGI (Cluster-Aware Generative Imputation), a framework that reformulates clustering and imputation as a mutually reinforcing co-optimization process.<n>Experiments on 14 benchmark datasets with 15 representative baselines demonstrate the superiority of CAGI.
  arXiv  Detail & Related papers  (2026-07-08T02:50:02Z)
• Hypernetwork-based approach for grid-independent functional data clustering [3.142113135607563]
  We introduce a framework that maps discretized function observations into a fixed-dimensional vector space via an auto-encoding architecture.<n>The encoder is a hypernetwork that maps coordinate-value pairs to the weight space of an implicit neural representation.<n>By means of synthetic and real-world experiments in high-dimensional settings, we demonstrate competitive clustering performance.
  arXiv  Detail & Related papers  (2026-02-26T10:05:07Z)
• Depth Completion as Parameter-Efficient Test-Time Adaptation [66.72360181325877]
  CAPA is a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion.<n>For videos, CAPA introduces sequence-level parameter sharing, jointly adapting all frames to exploit temporal correlations, improve robustness, and enforce multi-frame consistency.
  arXiv  Detail & Related papers  (2026-02-16T13:53:23Z)
• OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models [57.94189874119267]
  Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems.<n>Current graph learning-based design methodologies often adhere to a "one-for-one" paradigm.<n>We propose OFA-TAD, a one-for-all framework that generates adaptive collaboration graphs for any task described in natural language.
  arXiv  Detail & Related papers  (2026-01-19T12:23:44Z)
• UDFS: Lightweight Representation-Driven Robust Network Traffic Classification [6.702683003854296]
  textbfUDFS is a representation that compresses an entire trace into a two-dimensional sequence.<n>textbfUDFS achieves superior classification performance and robustness on coarse-grained and fine-grained datasets.
  arXiv  Detail & Related papers  (2025-09-14T08:27:20Z)
• HyperSORT: Self-Organising Robust Training with hyper-networks [1.1327019820428537]
  HyperSORT is a framework using a hyper-network predicting UNets' parameters from latent vectors representing both the image and annotation variability.<n>We validate our method on two 3D abdominal CT public datasets.<n>Latent space clusters yield UNet parameters performing the segmentation task in accordance with the underlying learned systematic bias.
  arXiv  Detail & Related papers  (2025-06-26T16:12:34Z)
• Scalable Context-Preserving Model-Aware Deep Clustering for Hyperspectral Images [51.95768218975529]
  Subspace clustering has become widely adopted for the unsupervised analysis of hyperspectral images (HSIs)<n>Recent model-aware deep subspace clustering methods often use a two-stage framework, involving the calculation of a self-representation matrix with complexity of O(n2), followed by spectral clustering.<n>We propose a scalable, context-preserving deep clustering method based on basis representation, which jointly captures local and non-local structures for efficient HSI clustering.
  arXiv  Detail & Related papers  (2025-06-12T16:43:09Z)
• Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World [7.9346432903946535]
  Deep neural networks still suffer performance declines under distribution shifts between training and test domains.<n>We propose Feature-based Instance Neighbor Discovery (FIND), which comprises three key components: Layer-wise Feature Disentanglement (LFD), Feature Aware Batch Normalization (FABN) and Selective FABN (S-FABN)<n>Experiments demonstrate FIND significantly outperforms existing methods, achieving a 30% accuracy improvement in dynamic scenarios.
  arXiv  Detail & Related papers  (2025-06-07T12:45:49Z)
• FlexPara: Flexible Neural Surface Parameterization [71.65203972602673]
  This paper introduces FlexPara, an unsupervised neural optimization framework to achieve both global and multi-chart surface parameterizations.<n>We ingeniously design and combine a series of geometrically-interpretable sub-networks, with specific functionalities, to construct a bi-directional cycle mapping framework for global parameterization.<n>Experiments demonstrate the universality, superiority, and inspiring potential of our neural surface parameterization paradigm.
  arXiv  Detail & Related papers  (2025-04-27T12:30:08Z)
• Modeling All Response Surfaces in One for Conditional Search Spaces [69.90317997694218]
  This paper proposes a novel approach to model the response surfaces of all subspaces in one.<n>We introduce an attention-based deep feature extractor, capable of projecting configurations with different structures from various subspaces into a unified feature space.
  arXiv  Detail & Related papers  (2025-01-08T03:56:06Z)
• A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [54.05517338122698]
  A popular similarity-based feature upsampling pipeline has been proposed, which utilizes a high-resolution feature as guidance.<n>We propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives.<n>We develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts.
  arXiv  Detail & Related papers  (2024-07-02T14:12:21Z)
• SparCA: Sparse Compressed Agglomeration for Feature Extraction and Dimensionality Reduction [0.0]
  We propose sparse compressed agglomeration (SparCA) as a novel dimensionality reduction procedure. SparCA is applicable to a wide range of data types, produces highly interpretable features, and shows compelling performance on downstream supervised learning tasks.
  arXiv  Detail & Related papers  (2023-01-26T13:59:15Z)
• UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection [37.03465340777392]
  Dimensional reduction(DR) maps high-dimensional data into a lower dimensions latent space with minimized defined optimization objectives. FS focuses on selecting a critical subset of dimensions but risks destroying the data distribution (structure) FP combines all the input features into lower dimensions space, aiming to maintain the data structure; but lacks interpretability and sparsity. We develop a unified framework, Unified Dimensional Reduction Neural-network(UDRN), that integrates FS and FP in a compatible, end-to-end way.
  arXiv  Detail & Related papers  (2022-07-08T10:30:20Z)
• DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture [81.82173855071312]
  We propose an end-to-end solution that integrates the AutoML components and returns a ready-to-use model at the end of the search. Dha achieves state-of-the-art (SOTA) results on various datasets, especially 77.4% accuracy on ImageNet with cell based search space.
  arXiv  Detail & Related papers  (2021-09-13T08:12:50Z)
• Dynamic Convolution for 3D Point Cloud Instance Segmentation [146.7971476424351]
  We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. We gather homogeneous points that have identical semantic categories and close votes for the geometric centroids. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
  arXiv  Detail & Related papers  (2021-07-18T09:05:16Z)

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.