Search Results for author:
Found 8 papers, 3 papers with code
FSD-Inference: Fully Serverless Distributed Inference with Scalable Cloud Communication
In the absence of such solutions in the serverless domain, parallel computation with significant IPC requirements is challenging.
Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
Graph Neural Network (GNN) training and inference involve significant challenges of scalability with respect to both model sizes and number of layers, resulting in degradation of efficiency and accuracy for large and deep GNNs.
Scalable Graph Convolutional Network Training on Distributed-Memory Systems
The large data sizes of graphs and their vertex features make scalable training algorithms and distributed memory systems necessary.
RAGUEL: Recourse-Aware Group Unfairness Elimination
While machine learning and ranking-based systems are in widespread use for sensitive decision-making processes (e. g., determining job candidates, assigning credit scores), they are rife with concerns over unintended biases in their outcomes, which makes algorithmic fairness (e. g., demographic parity, equal opportunity) an objective of interest.
GeoPointGAN: Synthetic Spatial Data with Local Label Differential Privacy
We introduce GeoPointGAN, a novel GAN-based solution for generating synthetic spatial point datasets with high utility and strong individual level privacy guarantees.
Partitioning sparse deep neural networks for scalable training and inference
Both the feedforward (inference) and backpropagation steps in stochastic gradient descent (SGD) algorithm for training sparse DNNs involve consecutive sparse matrix-vector multiplications (SpMVs).
VISIR: Visual and Semantic Image Label Refinement
CBIR now gains semantic expressiveness by advances in deep-learning-based detection of visual labels.
Characterizing the impact of geometric properties of word embeddings on task performance
Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors.
