Search Results for author:
Found 15 papers, 6 papers with code
Dynamic layer selection in decoder-only transformers
The vast size of Large Language Models (LLMs) has prompted a search to optimize inference.
Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
Machine learning models can solve complex tasks but often require significant computational resources during inference.
Interacting Diffusion Processes for Event Sequence Forecasting
Our model is composed of two diffusion processes, one for the time intervals and one for the event types.
Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN
Training an EDNN architecture is challenging as it consists of two intertwined components: the gating mechanism (GM) that controls early-exiting decisions and the intermediate inference modules (IMs) that perform inference from intermediate representations.
Diffusing Gaussian Mixtures for Generating Categorical Data
Learning a categorical distribution comes with its own set of challenges.
Evaluation of Categorical Generative Models -- Bridging the Gap Between Real and Synthetic Data
We validate our evaluation procedure with synthetic experiments on both synthetic generative models and current state-of-the-art categorical generative models.
Contrastive Learning for Time Series on Dynamic Graphs
We propose a framework called GraphTNC for unsupervised learning of joint representations of the graph and the time-series.
Node Copying: A Random Graph Model for Effective Graph Sampling
In this work, we introduce the node copying model for constructing a distribution over graphs.
Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks
Since a meaningful graph representing dependencies between bags is rarely available, we propose to use a Bayesian GNN framework that can generate a likely graph structure for scenarios where there is uncertainty in the graph or when no graph is available.
A Framework for Recommending Accurate and Diverse ItemsUsing Bayesian Graph Convolutional Neural Networks
Because of the multitude of relationships existing in recommender systems, Graph Neural Networks (GNNs) based approaches have been proposed to better characterize the various relationships between a user and items while modeling a user's preferences.
Node Copying for Protection Against Graph Neural Network Topology Attacks
With the increased interest in graph based machine learning techniques, there have been investigations which suggest that these models are also vulnerable to attacks.
Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation
Node classification in attributed graphs is an important task in multiple practical settings, but it can often be difficult or expensive to obtain labels.
Non-Parametric Graph Learning for Bayesian Graph Neural Networks
A Bayesian framework which targets posterior inference of the graph by considering it as a random quantity can be beneficial.
Bayesian Graph Convolutional Neural Networks using Node Copying
Graph convolutional neural networks (GCNN) have numerous applications in different graph based learning tasks.
Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
Graph convolutional neural networks (GCNN) have been successfully applied to many different graph based learning tasks including node and graph classification, matrix completion, and learning of node embeddings.
