SOTAVerified

Representation Learning

Representation Learning is a process in machine learning where algorithms extract meaningful patterns from raw data to create representations that are easier to understand and process. These representations can be designed for interpretability, reveal hidden features, or be used for transfer learning. They are valuable across many fundamental machine learning tasks like image classification and retrieval.

Deep neural networks can be considered representation learning models that typically encode information which is projected into a different subspace. These representations are then usually passed on to a linear classifier to, for instance, train a classifier.

Representation learning can be divided into:

  • Supervised representation learning: learning representations on task A using annotated data and used to solve task B
  • Unsupervised representation learning: learning representations on a task in an unsupervised way (label-free data). These are then used to address downstream tasks and reducing the need for annotated data when learning news tasks. Powerful models like GPT and BERT leverage unsupervised representation learning to tackle language tasks.

More recently, self-supervised learning (SSL) is one of the main drivers behind unsupervised representation learning in fields like computer vision and NLP.

Here are some additional readings to go deeper on the task:

( Image credit: Visualizing and Understanding Convolutional Networks )

Papers

Showing 92019250 of 10580 papers

TitleStatusHype
Representation Learning of EHR Data via Graph-Based Medical Entity Embedding0
Neural Multisensory Scene InferenceCode0
SCALOR: Generative World Models with Scalable Object RepresentationsCode0
Rethinking Kernel Methods for Node Representation Learning on GraphsCode0
Learning Robust Representations with Graph Denoising Policy Network0
High Mutual Information in Representation Learning with Symmetric Variational Inference0
Stacked Wasserstein Autoencoder0
Unsupervised Representation for EHR Signals and Codes as Patient Status Vector0
DPSOM: Deep Probabilistic Clustering with Self-Organizing MapsCode0
Animating Face using Disentangled Audio Representations0
Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning0
Self-Supervised Representation Learning From Multi-Domain Data0
Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced DataCode0
ERL-Net: Entangled Representation Learning for Single Image De-Raining0
Deep Clustering by Gaussian Mixture Variational Autoencoders With Graph EmbeddingCode0
A Large-scale Study of Representation Learning with the Visual Task Adaptation BenchmarkCode0
Spread-gram: A spreading-activation schema of network structural learning0
Equivariant Hamiltonian Flows0
Learning to Align Multi-Camera Domains using Part-Aware Clustering for Unsupervised Video Person Re-Identification0
Learning Robust Data Representation: A Knowledge Flow Perspective0
Facial Expression Recognition Using Disentangled Adversarial Learning0
Multi-Agent Actor-Critic with Hierarchical Graph Attention Network0
BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization0
Identifying Sparse Low-Dimensional Structures in Markov Chains: A Nonnegative Matrix Factorization Approach0
Federated User Representation Learning0
RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image SynthesisCode0
Identifying through Flows for Recovering Latent RepresentationsCode0
Representation Learning with Ordered Relation Paths for Knowledge Graph CompletionCode0
Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on GraphsCode0
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages0
DeepPCM: Predicting Protein-Ligand Binding using Unsupervised Learned Representations0
Improved Mutual Information Estimation0
Deep End-to-end Unsupervised Anomaly Detection0
DO-AutoEncoder: Learning and Intervening Bivariate Causal Mechanisms in Images0
Octave Graph Convolutional Network0
A bi-diffusion based layer-wise sampling method for deep learning in large graphs0
Privacy-preserving Representation Learning by Disentanglement0
ICNN: INPUT-CONDITIONED FEATURE REPRESENTATION LEARNING FOR TRANSFORMATION-INVARIANT NEURAL NETWORK0
Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood MatchingCode0
Self-Supervised Policy Adaptation0
MULTI-LABEL METRIC LEARNING WITH BIDIRECTIONAL REPRESENTATION DEEP NEURAL NETWORKS0
RISE and DISE: Two Frameworks for Learning from Time Series with Missing Data0
Attributed Graph Learning with 2-D Graph Convolution0
Efficient High-Dimensional Data Representation Learning via Semi-Stochastic Block Coordinate Descent Methods0
Consistency-Based Semi-Supervised Active Learning: Towards Minimizing Labeling Budget0
Reject Illegal Inputs: Scaling Generative Classifiers with Supervised Deep Infomax0
Hierarchical Disentangle Network for Object Representation Learning0
ROBUST DISCRIMINATIVE REPRESENTATION LEARNING VIA GRADIENT RESCALING: AN EMPHASIS REGULARISATION PERSPECTIVE0
An Information Theoretic Approach to Distributed Representation Learning0
Empowering Graph Representation Learning with Paired Training and Graph Co-Attention0
Show:102550
← PrevPage 185 of 212Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SciNCLAvg.81.8Unverified
2SPECTERAvg.80Unverified
3CiteomaticAvg.76Unverified
4Sci-DeCLUTRAvg.66.6Unverified
5SciBERTAvg.59.6Unverified
6BioBERTAvg.58.8Unverified
7CiteBERTAvg.58.8Unverified
#ModelMetricClaimedVerifiedStatus
1top_model_weights_with_3d_21:1 Accuracy0.75Unverified
#ModelMetricClaimedVerifiedStatus
1Resnet 18Accuracy (%)97.05Unverified
#ModelMetricClaimedVerifiedStatus
1Morphological NetworkAccuracy97.3Unverified
#ModelMetricClaimedVerifiedStatus
1Max Margin ContrastiveSilhouette Score0.56Unverified