In this paper, we explore a novel knowledge-transfer task, termed as Deep Model Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …
In this paper, we study dataset distillation (DD), from a novel perspective and introduce a\emph {dataset factorization} approach, termed\emph {HaBa}, which is a plug-and-play …
X Yang, J Ye, X Wang - European Conference on Computer Vision, 2022 - Springer
In this paper, we explore a novel and ambitious knowledge-transfer task, termed Knowledge Factorization (KF). The core idea of KF lies in the modularization and assemblability of …
Learning to predict agent motions with relationship reasoning is important for many applications. In motion prediction tasks, maintaining motion equivariance under Euclidean …
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation …
S Fan, X Wang, Y Mo, C Shi… - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by learning the correlation between the input graphs and labels. However, by presenting a …
Y Liu, K Wang, L Liu, H Lan, L Lin - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective …
Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to …
In this paper, we explore a novel model reusing task tailored for graph neural networks (GNNs), termed as" deep graph reprogramming". We strive to reprogram a pre-trained GNN …