Related papers: CARL: Content-Aware Representation Learning for He…

Aggregated search aims to construct search result pages (SERPs) from blue-links and heterogeneous modules (such as news, images, and videos). Existing studies have largely ignored the correlations between blue-links and heterogeneous…

In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an…

Both reviews and user-item interactions (i.e., rating scores) have been widely adopted for user rating prediction. However, these existing techniques mainly extract the latent representations for users and items in an independent and static…

We introduce Consistent Assignment for Representation Learning (CARL), an unsupervised learning method to learn visual representations by combining ideas from self-supervised contrastive learning and deep clustering. By viewing contrastive…

Inductive representation learning on temporal heterogeneous graphs is crucial for scalable deep learning on heterogeneous information networks (HINs) which are time-varying, such as citation networks. However, most existing approaches are…

Representation learning on heterogeneous graphs aims to obtain meaningful node representations to facilitate various downstream tasks, such as node classification and link prediction. Existing heterogeneous graph learning methods are…

The inception of modeling contextual information using models such as BERT, ELMo, and Flair has significantly improved representation learning for words. It has also given SOTA results in almost every NLP task - Machine Translation, Text…

Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual…

Heterogeneous graphs with heterophily have emerged as a powerful abstraction for modeling complex real-world systems, where nodes of different types and labels interact in diverse and often non-homophilous ways. Despite recent advances,…

Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding, and is already established as a critical modality in remote sensing. However, variability in channel dimensionality and…

Complementary recommendations play a crucial role in e-commerce by enhancing user experience through suggestions of compatible items. Accurate classification of complementary item relationships requires reliable labels, but their creation…

Prognostic Health Management (PHM) systems monitor and predict equipment health. A key task is Remaining Useful Life (RUL) estimation, which predicts how long a component, such as a rolling element bearing, will operate before failure. Many…

Performance predictors have emerged as a promising method to accelerate the evaluation stage of neural architecture search (NAS). These predictors estimate the performance of unseen architectures by learning from the correlation between a…

A major challenge in modern reinforcement learning (RL) is efficient control of dynamical systems from high-dimensional sensory observations. Learning controllable embedding (LCE) is a promising approach that addresses this challenge by…

Graph representation learning (GRL) has emerged as an effective technique for modeling graph-structured data. When modeling heterogeneity and dynamics in real-world complex networks, GRL methods designed for complex heterogeneous temporal…

Network representation aims to represent the nodes in a network as continuous and compact vectors, and has attracted much attention in recent years due to its ability to capture complex structure relationships inside networks. However,…

Exploring the narratives conveyed by fine-art paintings is a challenge in image captioning, where the goal is to generate descriptions that not only precisely represent the visual content but also offer a in-depth interpretation of the…

Heterogeneous graphs can well describe the complex entity relationships in the real world. For example, online shopping networks contain multiple physical types of consumers and products, as well as multiple relationship types such as…

Hypergraph representation learning has garnered increasing attention across various domains due to its capability to model high-order relationships. Traditional methods often rely on hypergraph neural networks (HNNs) employing message…

Flashcard schedulers rely on 1) student models to predict the flashcards a student knows; and 2) teaching policies to pick which cards to show next via these predictions. Prior student models, however, just use study data like the student's…