Related papers: TA-KAND: Two-stage Attention Triple Enhancement an…

As a technically challenging topic, visual storytelling aims at generating an imaginary and coherent story with narrative multi-sentences from a group of relevant images. Existing methods often generate direct and rigid descriptions of…

Whole-Slide Imaging allows for the capturing and digitization of high-resolution images of histological specimen. An automated analysis of such images using deep learning models is therefore of high demand. The transformer architecture has…

We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current…

3D Human motion style transfer is a fundamental problem in computer graphic and animation processing. Existing AdaIN- based methods necessitate datasets with balanced style distribution and content/style labels to train the clustered latent…

Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to training data. Although diffusion models are adept…

Exemplar-Free Continual Learning (EFCL) restricts the storage of previous task data and is highly susceptible to catastrophic forgetting. While pre-trained models (PTMs) are increasingly leveraged for EFCL, existing methods often overlook…

We propose KAHAN, a knowledge-augmented hierarchical framework that systematically extracts insights from raw tabular data at entity, pairwise, group, and system levels. KAHAN uniquely leverages LLMs as domain experts to drive the analysis.…

Expanding existing learning systems to provide high-quality customized models for more domains, such as new users, is challenged by the limited labeled data and the data and device heterogeneities. While knowledge distillation methods could…

Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed…

End-to-end question answering using a differentiable knowledge graph is a promising technique that requires only weak supervision, produces interpretable results, and is fully differentiable. Previous implementations of this technique…

Existing research usually utilizes side information such as social network or item attributes to improve the performance of collaborative filtering-based recommender systems. In this paper, the knowledge graph with user perception is used…

Graph Neural Networks (GNNs) are the go-to model for graph data analysis. However, GNNs rely on two key operations - aggregation and update, which can pose challenges for low-latency inference tasks or resource-constrained scenarios. Simple…

Knowledge distillation is a powerful technique for transferring knowledge from a pre-trained teacher model to a student model. However, the true potential of knowledge transfer has not been fully explored. Existing approaches primarily…

Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In…

Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers…

A comprehensive knowledge graph (KG) contains an instance-level entity graph and an ontology-level concept graph. The two-view KG provides a testbed for models to "simulate" human's abilities on knowledge abstraction, concretization, and…

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

As an important and challenging problem, few-shot image generation aims at generating realistic images through training a GAN model given few samples. A typical solution for few-shot generation is to transfer a well-trained GAN model from a…

Knowledge Graph (KG) completion research usually focuses on densely connected benchmark datasets that are not representative of real KGs. We curate two KG datasets that include biomedical and encyclopedic knowledge and use an existing…

In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations. Most of the existing methods conducted on HIN revise…