Related papers: Multi-View Reasoning: Consistent Contrastive Learn…
Multi-view learning is frequently used in data science. The pairwise correlation maximization is a classical approach for exploring the consensus of multiple views. Since the pairwise correlation is inherent for two views, the extensions to…
Resolving conflicts is critical for improving the reliability of multi-view classification. While prior work focuses on learning consistent and informative representations across views, it often assumes perfect alignment and equal…
Multi-view representation learning is essential for many multi-view tasks, such as clustering and classification. However, there are two challenging problems plaguing the community: i)how to learn robust multi-view representation from mass…
The effectiveness of contrastive learning in sequential recommendation hinges on the construction of contrastive views, which ideally should be both semantically consistent and diverse. However, most existing CL-based methods rely on…
This work explores enabling Chain-of-Thought (CoT) reasoning to link visual cues across multiple images. A straightforward solution is to adapt rule-based reinforcement learning for Vision-Language Models (VLMs). However, such methods…
Math word problems form a natural abstraction to a range of quantitative reasoning problems, such as understanding financial news, sports results, and casualties of war. Solving such problems requires the understanding of several…
Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems involving both textual and visual modalities. However, current models still face significant challenges in…
Graph-level contrastive learning, aiming to learn the representations for each graph by contrasting two augmented graphs, has attracted considerable attention. Previous studies usually simply assume that a graph and its augmented graph as a…
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less…
Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance…
The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on the construction side, both handcrafted and generative…
Multiview clustering (MVC) segregates data samples into meaningful clusters by synthesizing information across multiple views. Moreover, deep learning-based methods have demonstrated their strong feature learning capabilities in MVC…
Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused…
Selecting an appropriate response from many candidates given the utterances in a multi-turn dialogue is the key problem for a retrieval-based dialogue system. Existing work formalizes the task as matching between the utterances and a…
Existing multi-style image captioning methods show promising results in generating a caption with accurate visual content and desired linguistic style. However, existing methods overlook the relationship between linguistic style and visual…
Multi-view representation learning aims to capture comprehensive information from multiple views of a shared context. Recent works intuitively apply contrastive learning to different views in a pairwise manner, which is still scalable:…
Many recent approaches in representation learning implicitly assume that uncorrelated views of a data point are sufficient to learn meaningful representations for various downstream tasks. In this work, we challenge this assumption and…
Cross-modal retrieval is the task of retrieving samples of a given modality by using queries of a different one. Due to the wide range of practical applications, the problem has been mainly focused on the vision and language case, e.g. text…
Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an…
In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…