{"url":"/method/hypernetwork","slug":"hypernetwork","name":"HyperNetwork","full_name":"HyperNetwork","full_name_withheld":false,"description_markdown":"A **HyperNetwork** is a network that generates weights for a main network.  The behavior of the main network is the same with any usual neural network: it learns to map some raw inputs to their desired targets; whereas the hypernetwork takes a set of inputs that contain information about the structure of the weights and generates the weight for that layer.","description_state":"present","introduced_year":null,"introduced_by":{"title":"HyperNetworks","paper":"/paper/hypernetworks","first_author":"David Ha","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/hypernetworks"},"source":{"url":"http://arxiv.org/abs/1609.09106v4","title":"HyperNetworks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/g1910/HyperNetworks/blob/393e30a56c2ba14fa9efee5f2698d8c82e5821f6/hypernetwork_modules.py#L6","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Feedforward Networks","url":"/methods/category/feedforward-networks","pwc_aliases":[]}],"n_papers_tagged":239,"archive_num_papers":239,"papers_newest_first":[{"paper":null,"title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","date":"2025-07-07","arxiv_id":"2507.10446","n_code_links":0,"syntology":null},{"paper":null,"title":"Beyond Static Models: Hypernetworks for Adaptive and Generalizable Forecasting in Complex Parametric Dynamical Systems","date":"2025-06-24","arxiv_id":"2506.19609","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning Personalized Utility Functions for Drivers in Ride-hailing Systems Using Ensemble Hypernetworks","date":"2025-06-21","arxiv_id":"2506.17672","n_code_links":0,"syntology":null},{"paper":null,"title":"LFR-PINO: A Layered Fourier Reduced Physics-Informed Neural Operator for Parametric PDEs","date":"2025-06-21","arxiv_id":"2506.17582","n_code_links":0,"syntology":null},{"paper":"/paper/generalizable-agent-modeling-for-agent","title":"Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation","date":"2025-06-20","arxiv_id":"2506.16718","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-external-factors-in-household","title":"Leveraging External Factors in Household-Level Electrical Consumption Forecasting using Hypernetworks","date":"2025-06-17","arxiv_id":"2506.14472","n_code_links":1,"syntology":null},{"paper":"/paper/propmend-hypernetworks-for-knowledge","title":"PropMEND: Hypernetworks for Knowledge Propagation in LLMs","date":"2025-06-10","arxiv_id":"2506.08920","n_code_links":1,"syntology":null},{"paper":null,"title":"SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense","date":"2025-06-09","arxiv_id":"2506.08255","n_code_links":0,"syntology":null},{"paper":null,"title":"ExARNN: An Environment-Driven Adaptive RNN for Learning Non-Stationary Power Dynamics","date":"2025-05-23","arxiv_id":"2505.17488","n_code_links":0,"syntology":null},{"paper":null,"title":"Neural Conditional Transport Maps","date":"2025-05-21","arxiv_id":"2505.15808","n_code_links":0,"syntology":null},{"paper":null,"title":"Editing Across Languages: A Survey of Multilingual Knowledge Editing","date":"2025-05-20","arxiv_id":"2505.14393","n_code_links":0,"syntology":null},{"paper":null,"title":"Relation-Aware Graph Foundation Model","date":"2025-05-17","arxiv_id":"2505.12027","n_code_links":0,"syntology":null},{"paper":"/paper/disco-learning-to-discover-an-evolution","title":"DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction","date":"2025-04-28","arxiv_id":"2504.19496","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Uncertainty quantification of neural network models of evolving processes via Langevin sampling","date":"2025-04-21","arxiv_id":"2504.14854","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-allocation-hypernetwork-with-adaptive-1","title":"Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for Federated Continual Learning","date":"2025-03-25","arxiv_id":"2503.20808","n_code_links":1,"syntology":null},{"paper":"/paper/continual-reinforcement-learning-for-hvac","title":"Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer Learning","date":"2025-03-24","arxiv_id":"2503.19212","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-allocation-hypernetwork-with-adaptive","title":"Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCL","date":"2025-03-23","arxiv_id":"2503.18064","n_code_links":1,"syntology":null},{"paper":null,"title":"HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks","date":"2025-03-21","arxiv_id":"2503.17276","n_code_links":0,"syntology":null},{"paper":null,"title":"HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks","date":"2025-03-13","arxiv_id":"2503.10894","n_code_links":0,"syntology":null},{"paper":null,"title":"HyDA: Hypernetworks for Test Time Domain Adaptation in Medical Imaging Analysis","date":"2025-03-06","arxiv_id":"2503.04979","n_code_links":0,"syntology":null},{"paper":"/paper/a-hypernetwork-based-approach-to-kan","title":"A Hypernetwork-Based Approach to KAN Representation of Audio Signals","date":"2025-03-04","arxiv_id":"2503.02585","n_code_links":1,"syntology":null},{"paper":null,"title":"Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models","date":"2025-03-02","arxiv_id":"2503.00838","n_code_links":0,"syntology":null},{"paper":null,"title":"Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation","date":"2025-02-18","arxiv_id":"2502.12492","n_code_links":0,"syntology":null},{"paper":"/paper/2502-05759","title":"Reinforced Lifelong Editing for Language Models","date":"2025-02-09","arxiv_id":"2502.05759","n_code_links":1,"syntology":null},{"paper":null,"title":"Leveraging Hypernetworks and Learnable Kernels for Consumer Energy Forecasting Across Diverse Consumer Types","date":"2025-02-07","arxiv_id":"2502.05104","n_code_links":0,"syntology":null},{"paper":null,"title":"Discovering Physics Laws of Dynamical Systems via Invariant Function Learning","date":"2025-02-06","arxiv_id":"2502.04495","n_code_links":0,"syntology":null},{"paper":"/paper/dual-ensembled-multiagent-q-learning-with","title":"Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer","date":"2025-02-04","arxiv_id":"2502.02018","n_code_links":1,"syntology":null},{"paper":null,"title":"Multi-frequency wavefield solutions for variable velocity models using meta-learning enhanced low-rank physics-informed neural network","date":"2025-02-02","arxiv_id":"2502.00897","n_code_links":0,"syntology":null},{"paper":null,"title":"ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learning","date":"2025-01-27","arxiv_id":"2501.16002","n_code_links":0,"syntology":null},{"paper":null,"title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","date":"2025-01-12","arxiv_id":"2501.06773","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/federated-learning","name":"Federated Learning","papers":17},{"task":"/task/meta-learning","name":"Meta-Learning","papers":17},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":15},{"task":"/task/continual-learning","name":"Continual Learning","papers":13},{"task":"/task/decoder","name":"Decoder","papers":11},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":11},{"task":"/task/nerf","name":"NeRF","papers":10},{"task":"/task/personalized-federated-learning","name":"Personalized Federated Learning","papers":9},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":9},{"task":"/task/diversity","name":"Diversity","papers":8},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":8},{"task":"/task/prediction","name":"Prediction","papers":8},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":8},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":8},{"task":"/task/image-generation","name":"Image Generation","papers":7},{"task":"/task/super-resolution","name":"Super-Resolution","papers":7},{"task":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","papers":7},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":6},{"task":"/task/language-modelling","name":"Language Modelling","papers":6},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":6}],"tasks_shown":20,"n_tasks":251,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":3},{"year":"2018","papers":5},{"year":"2019","papers":7},{"year":"2020","papers":15},{"year":"2021","papers":31},{"year":"2022","papers":42},{"year":"2023","papers":50},{"year":"2024","papers":53},{"year":"2025","papers":32}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/hypernetwork"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}