To the best of our knowledge, our theoretical result is among the first to theoretically demonstrate the advantage of low-rank learning in graph contrastive learning supported by strong empirical performance.
no code implementations • 22 Jan 2024 • Hong Guan, Summer Gautier, Deepti Gupta, Rajan Hari Ambrish, Yancheng Wang, Harsha Lakamsani, Dhanush Giriyan, Saajan Maslanka, Chaowei Xiao, Yingzhen Yang, Jia Zou
It is challenging to balance the privacy and accuracy for federated query processing over multiple private data silos.
While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability to leverage external knowledge due to model scale and data size constraints.
In this paper, we propose Robust Neural Architecture Search by Cross-Layer Knowledge Distillation (RNAS-CL), a novel NAS algorithm that improves the robustness of NAS by learning from a robust teacher through cross-layer knowledge distillation.
Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars.
In this work, we propose a novel and robust method, Bayesian Robust Graph Contrastive Learning (BRGCL), which trains a GNN encoder to learn robust node representations.
In general, the contrastive learning process in GCL is performed on top of the representations learned by a graph neural network (GNN) backbone, which transforms and propagates the node contextual information based on its local neighborhoods.
Embedding RMML into the proposed ECML mechanism, our metric learning paradigm (EC-RMML) can run in the one-pass learning manner.
Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly.
To better exploit three-dimensional (3D) characteristics, multi-view dynamic images are proposed.