Related papers: Constructing Enhanced Mutual Information for Onlin…

Multimodal representation learning poses significant challenges in capturing informative and distinct features from multiple modalities. Existing methods often struggle to exploit the unique characteristics of each modality due to unified…

Recent contrastive representation learning methods rely on estimating mutual information (MI) between multiple views of an underlying context. E.g., we can derive multiple views of a given image by applying data augmentation, or we can…

Estimating mutual information between continuous random variables is often intractable and extremely challenging for high-dimensional data. Recent progress has leveraged neural networks to optimize variational lower bounds on mutual…

Learning representations that transfer well to diverse downstream tasks remains a central challenge in representation learning. Existing paradigms -- contrastive learning, self-supervised masking, and denoising auto-encoders -- balance this…

We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual…

The concepts of conditional mutual information (CMI) and normalized conditional mutual information (NCMI) are introduced to measure the concentration and separation performance of a classification deep neural network (DNN) in the output…

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate…

A new trend in deep learning, represented by Mutual Information Neural Estimation (MINE) and Information Noise Contrast Estimation (InfoNCE), is emerging. In this trend, similarity functions and Estimated Mutual Information (EMI) are used…

Learning representations that generalize well to unknown downstream tasks is a central challenge in representation learning. Existing approaches such as contrastive learning, self-supervised masking, and denoising auto-encoders address this…

Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams can be seen only once, it is more suitable for real-world scenarios compared to offline learning.…

In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this…

Class-incremental learning (CIL) enables models to continuously learn new categories from sequential tasks without forgetting previously acquired knowledge. While recent advances in vision-language models such as CLIP have demonstrated…

In this paper, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories. We initiate the study of data…

Mutual Information (MI) plays an important role in representation learning. However, MI is unfortunately intractable in continuous and high-dimensional settings. Recent advances establish tractable and scalable MI estimators to discover…

Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data. However, traditional MML methods generally use the…

Many applications in image-guided surgery and therapy require fast and reliable non-linear, multi-modal image registration. Recently proposed unsupervised deep learning-based registration methods have demonstrated superior performance…

The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation. Recently, the disentangle and fuse methods have achieved…

As interpretability gains attention in machine learning, there is a growing need for reliable models that fully explain representation content. We propose a mutual information (MI)-based method that decomposes neural network representations…

Online Class-Incremental (OCI) learning has sparked new approaches to expand the previously trained model knowledge from sequentially arriving data streams with new classes. Unfortunately, OCI learning can suffer from catastrophic…

In this paper, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed Cross-Modal Info-Max Hashing…