Related papers: Multimodal Information Bottleneck: Learning Minima…

Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount of synchronized, complete multimodal data. However, such a…

The Information Bottleneck (IB) method (\cite{tishby2000information}) provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective $I(X;Z)-\beta I(Y;Z)$ employs a…

Multi-task learning (MTL) is an important subject in machine learning and artificial intelligence. Its applications to computer vision, signal processing, and speech recognition are ubiquitous. Although this subject has attracted…

Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each…

Active learning for continuous regression has lacked an acquisition function that targets epistemic uncertainty when the predictive distribution is multimodal: variance misses modal disagreement, and information-theoretic targets like BALD…

The integration of multimodal information into sequential recommender systems has attracted significant attention in recent research. In the initial stages of multimodal sequential recommendation models, the mainstream paradigm was…

In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…

Deep learning has become the most powerful machine learning tool in the last decade. However, how to efficiently train deep neural networks remains to be thoroughly solved. The widely used minibatch stochastic gradient descent (SGD) still…

Deep learning methods have revolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial…

We view the Information Bottleneck Principle (IBP: Tishby et al., 1999; Schwartz-Ziv and Tishby, 2017) and Predictive Information Bottleneck Principle (PIBP: Still et al., 2007; Alemi, 2019) as special cases of a family of general…

Collaborative perception systems leverage multiple edge devices, such surveillance cameras or autonomous cars, to enhance sensing quality and eliminate blind spots. Despite their advantages, challenges such as limited channel capacity and…

Math Word Problems (MWP) aims to automatically solve mathematical questions given in texts. Previous studies tend to design complex models to capture additional information in the original text so as to enable the model to gain more…

Estimating the dimensionality of the latent representation needed for prediction -- the task-relevant dimension -- is a difficult, largely unsolved problem with broad scientific applications. We cast it as an Information Bottleneck…

Multimodal recommendation aims to enhance user preference modeling by leveraging rich item content such as images and text. Yet dominant systems fuse modalities in the spatial domain, obscuring the frequency structure of signals and…

The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of…

Multimodal recommender systems (MRS) improve recommendation performance by integrating complementary semantic information from multiple modalities. However, the assumption of complete multimodality rarely holds in practice due to missing…

Link prediction aims to identify potential missing triples in knowledge graphs. To get better results, some recent studies have introduced multimodal information to link prediction. However, these methods utilize multimodal information…

We propose a new approach to train a variational information bottleneck (VIB) that improves its robustness to adversarial perturbations. Unlike the traditional methods where the hard labels are usually used for the classification task, we…

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics,…

Although existing CLIP-based methods for detecting AI-generated images have achieved promising results, they are still limited by severe feature redundancy, which hinders their generalization ability. To address this issue, incorporating an…