Search Results for author:
Found 3 papers, 1 papers with code
Proteus: Preserving Model Confidentiality during Graph Optimizations
Development of new DL models typically involves two parties: the model developers and performance optimizers.
TDCGL: Two-Level Debiased Contrastive Graph Learning for Recommendation
Specifically, we design the Two-Level Debiased Contrastive Learning (TDCL) and deploy it in the KG, which is conducted not only on User-Item pairs but also on User-User pairs for modeling higher-order relations.
A Runtime-Based Computational Performance Predictor for Deep Neural Network Training
Our technique exploits the observation that, because DNN training consists of repetitive compute steps, predicting the execution time of a single iteration is usually enough to characterize the performance of an entire training process.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
