Related papers: InfoNCE Induces Gaussian Distribution
Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downstream tasks. However, these node representations remain opaque and difficult to interpret.…
The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant…
Contrastive learning is a recent promising approach in unsupervised representation learning where a feature representation of data is learned by solving a pseudo classification problem from unlabelled data. However, it is not…
Analyzing neural network dynamics via stochastic gradient descent (SGD) is crucial to building theoretical foundations for deep learning. Previous work has analyzed structured inputs within the \textit{hidden manifold model}, often under…
This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples. In contrast to the standard InfoNCE loss, which requires a strict…
Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL embeds the features extracted from neural networks onto…
We prove an exact relationship between the optimal denoising function and the data distribution in the case of additive Gaussian noise, showing that denoising implicitly models the structure of data allowing it to be exploited in the…
The success of machine learning methods heavily relies on having an appropriate representation for data at hand. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural…
Contrastive learning is a powerful technique to learn representations that are semantically distinctive and geometrically invariant. While most of the earlier approaches have demonstrated its effectiveness on single-modality learning tasks…
Modern neural recording techniques such as two-photon imaging or Neuropixel probes allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework…
Contrastive learning (CL) has recently been applied to adversarial learning tasks. Such practice considers adversarial samples as additional positive views of an instance, and by maximizing their agreements with each other, yields better…
Multi-modal generative AI systems, such as those combining vision and language, rely on contrastive pre-training to learn representations across different modalities. While their practical benefits are widely acknowledged, a rigorous…
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds. Despite promising progress, existing representations learned with…
Self-supervised contrastive learning (SSCL) has emerged as a powerful paradigm for representation learning and has been studied from multiple perspectives, including mutual information and geometric viewpoints. However, supervised…
We study the problem of learning causal representations from unknown, latent interventions in a general setting, where the latent distribution is Gaussian but the mixing function is completely general. We prove strong identifiability…
What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…
Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling…
This paper proposes a method for representation learning of multimodal data using contrastive losses. A traditional approach is to contrast different modalities to learn the information shared between them. However, that approach could fail…
Graph representation learning nowadays becomes fundamental in analyzing graph-structured data. Inspired by recent success of contrastive methods, in this paper, we propose a novel framework for unsupervised graph representation learning by…
It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing…