No article text was recorded for this version.
architectural inductive bias (random weight feature extraction)
Version 1 of 135 papers54 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On Evaluation Metrics for Graph Generative Models
- Blog: How Powerful is Graph Convolution for Recommendation?
- Blog: Graph Random Neural Features for Distance-Preserving Graph Representations
- Blog: Fast and Deep Graph Neural Networks
- Blog: Efficient quantification on large-scale networks
- Blog: On Stealing Graph Neural Network Models
- Blog: Pyramidal Reservoir Graph Neural Network
- Blog: An Untrained Neural Model for Fast and Accurate Graph Classification
- Blog: The First Learning on Graphs Conference: Preface
- Blog: InfraredGP: Efficient Graph Partitioning via Spectral Graph Neural Networks with Negative Corrections
- Blog: Pyramidal Graph Echo State Networks
- Blog: DataDAM: Efficient Dataset Distillation with Attention Matching
- Blog: Probing Graph Representations
- Blog: The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
- Blog: G-CREWE: Graph CompREssion With Embedding for Network Alignment
- Blog: Fine-grained Expressivity of Graph Neural Networks
- Blog: Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation
- Blog: RaftGP: Random Fast Graph Partitioning
- Blog: Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
- Blog: Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices
- Blog: Dataset Condensation with Distribution Matching
- Blog: Accurate and Scalable Graph Neural Networks via Message Invariance
- Blog: Face detection in untrained deep neural networks
- Blog: Untrained perceptual loss for image denoising of line-like structures in MRimages
- Blog: Training-free Graph Neural Networks and the Power of Labels as Features
- Blog: An Empirical Study of Over-Parameterized Neural Models based on Graph Random Features
- Blog: Mean-field theory of graph neural networks in graph partitioning
- Blog: Decoding Projections From Frozen Random Weights in Autoencoders: What Information Do They Encode?
- Blog: Few-shot learning for inference in medical imaging with subspace feature representations
- Blog: QUINT: Node Embedding Using Network Hashing
- Blog: Hashing-Accelerated Graph Neural Networks for Link Prediction
- Blog: Investigating over-parameterized randomized graph networks
- Blog: Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment
- Blog: GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
- Blog: Active Learning for Graph Neural Networks via Node Feature Propagation
History & citation
Current · Permanent link
- This direction split from The Inductive Bias of Untrained Graph Neural Networks (69% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_inductive_bias_random_weig_2aa586e8,
title = {architectural inductive bias (random weight feature extraction)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-inductive-bias-random-weight-feature-extraction/rdr_2aa586e8b9c140ffa4e844a18489f911},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_architectural_inductive_bias_random_weig_2aa586e8_v1,
title = {architectural inductive bias (random weight feature extraction)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-inductive-bias-random-weight-feature-extraction/rdr_2aa586e8b9c140ffa4e844a18489f911/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}