Representation Learning

3636 papers with code • 5 benchmarks • 9 datasets

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 )

Libraries

Use these libraries to find Representation Learning models and implementations

Latest papers with no code

AKBR: Learning Adaptive Kernel-based Representations for Graph Classification

no code yet • 24 Mar 2024

In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification.

Edit3K: Universal Representation Learning for Video Editing Components

no code yet • 24 Mar 2024

Each video in our dataset is rendered by various image/video materials with a single editing component, which supports atomic visual understanding of different editing components.

PSHop: A Lightweight Feed-Forward Method for 3D Prostate Gland Segmentation

no code yet • 24 Mar 2024

Automatic prostate segmentation is an important step in computer-aided diagnosis of prostate cancer and treatment planning.

Identifiable Latent Neural Causal Models

no code yet • 23 Mar 2024

This work establishes a {sufficient} and {necessary} condition characterizing the types of distribution shifts for identifiability in the context of latent additive noise models.

Contrastive Learning on Multimodal Analysis of Electronic Health Records

no code yet • 22 Mar 2024

To accommodate the statistical analysis of multimodal EHR data, in this paper, we propose a novel multimodal feature embedding generative model and design a multimodal contrastive loss to obtain the multimodal EHR feature representation.

Trajectory Regularization Enhances Self-Supervised Geometric Representation

no code yet • 22 Mar 2024

To address this gap, we introduce a new pose-estimation benchmark for assessing SSL geometric representations, which demands training without semantic or pose labels and achieving proficiency in both semantic and geometric downstream tasks.

Brain-grounding of semantic vectors improves neural decoding of visual stimuli

no code yet • 22 Mar 2024

To address this issue, we propose a representation learning framework, termed brain-grounding of semantic vectors, which fine-tunes pretrained feature vectors to better align with the neural representation of visual stimuli in the human brain.

Self-Supervised Backbone Framework for Diverse Agricultural Vision Tasks

no code yet • 22 Mar 2024

Computer vision in agriculture is game-changing with its ability to transform farming into a data-driven, precise, and sustainable industry.

Cell Variational Information Bottleneck Network

no code yet • 22 Mar 2024

In this work, we propose Cell Variational Information Bottleneck Network (cellVIB), a convolutional neural network using information bottleneck mechanism, which can be combined with the latest feedforward network architecture in an end-to-end training method.

Multiple-Input Auto-Encoder Guided Feature Selection for IoT Intrusion Detection Systems

no code yet • 22 Mar 2024

The MIAE model is trained in an unsupervised learning mode to transform the heterogeneous inputs into lower-dimensional representation, which helps classifiers distinguish between normal behaviour and different types of attacks.