相关论文: MuGSI: Distilling GNNs with Multi-Granularity Stru…

Feature distillation is an effective way to improve the performance for a smaller student model, which has fewer parameters and lower computation cost compared to the larger teacher model. Unfortunately, there is a common obstacle - the gap…

Classification tasks in 3D point clouds often assume that class events \replaced{are }{follow }independent and identically distributed (IID), although this assumption destroys the correlation between classes. This \replaced{study }{paper…

As graph data grows increasingly complicate, training graph neural networks (GNNs) on large-scale datasets presents significant challenges, including computational resource constraints, data redundancy, and transmission inefficiencies.…

Spiking Neural Networks (SNNs) become popular due to excellent energy efficiency, yet facing challenges for effective model training. Recent works improve this by introducing knowledge distillation (KD) techniques, with the pre-trained…

Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from a high-capacity teacher model to a smaller student model by aligning their output distributions. However, existing methods often underperform in…

GNNs, like other deep learning models, are data and computation hungry. There is a pressing need to scale training of GNNs on large datasets to enable their usage on low-resource environments. Graph distillation is an effort in that…

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…

Graph neural networks (GNNs) are prominent for their effectiveness in processing graph data for semi-supervised node classification tasks. Most works of GNNs assume that the observed structure accurately represents the underlying node…

Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges in Knowledge Distillation (KD) are: 1) balancing learning…

Graph Neural Networks (GNNs) have demonstrated remarkable results in various real-world applications, including drug discovery, object detection, social media analysis, recommender systems, and text classification. In contrast to their vast…

Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their voluminous parameters. To tackle this issue, Teacher-Student…

Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned…

Graph convolutional networks (GCNs) have been employed as a kind of significant tool on many graph-based applications recently. Inspired by convolutional neural networks (CNNs), GCNs generate the embeddings of nodes by aggregating the…

Document-level knowledge graph (KG) construction faces a fundamental scaling challenge: existing methods either rely on expensive large language models (LLMs), making them economically nonviable for large-scale corpora, or employ smaller…

Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring distilled knowledge…

3D Gaussian Splatting (3DGS) has exhibited remarkable efficacy in novel view synthesis (NVS). However, it suffers from a significant drawback: achieving high-fidelity rendering typically necessitates a large number of 3D Gaussians,…

Though convolutional neural networks are widely used in different tasks, lack of generalization capability in the absence of sufficient and representative data is one of the challenges that hinder their practical application. In this paper,…

Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher. However, applying KD in image regression with a…

The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature…

Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs). However, recent KGE models achieve performance improvements by excessively increasing the embedding…