Search Results for author:
Found 19 papers, 7 papers with code
Robust Image Watermarking using Stable Diffusion
Watermarking images is critical for tracking image provenance and claiming ownership.
Efficient IoT Inference via Context-Awareness
While existing strategies to execute deep learning-based classification on low-power platforms assume the models are trained on all classes of interest, this paper posits that adopting context-awareness i. e. narrowing down a classification task to the current deployment context consisting of only recent inference queries can substantially enhance performance in resource-constrained environments.
Multi-Task Models Adversarial Attacks
We then introduce a novel attack framework, the Gradient Balancing Multi-Task Attack (GB-MTA), which treats attacking a multi-task model as an optimization problem.
Structured Pruning for Multi-Task Deep Neural Networks
Numerous structured pruning methods are already developed that can readily achieve speedups in single-task models, but the pruning of multi-task networks has not yet been extensively studied.
GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism
Large-scale graphs with billions of edges are ubiquitous in many industries, science, and engineering fields such as recommendation systems, social graph analysis, knowledge base, material science, and biology.
Automatically Marginalized MCMC in Probabilistic Programming
Hamiltonian Monte Carlo (HMC) is a powerful algorithm to sample latent variables from Bayesian models.
Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing
Current approaches to personalization in FL are at a coarse granularity, i. e. all the input instances of a client use the same personalized model.
Uplifting Message Passing Neural Network with Graph Original Information
Message passing neural networks (MPNNs) learn the representation of graph-structured data based on graph original information, including node features and graph structures, and have shown astonishing improvement in node classification tasks.
Ranked #5 on
Node Classification
on arXiv-year
Improving Subgraph Representation Learning via Multi-View Augmentation
Subgraph representation learning based on Graph Neural Network (GNN) has exhibited broad applications in scientific advancements, such as predictions of molecular structure-property relationships and collective cellular function.
A Tree-Structured Multi-Task Model Recommender
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL).
Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression
This paper investigates deep neural network (DNN) compression from the perspective of compactly representing and storing trained parameters.
COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression
In this paper, we propose a novel memory-efficient CNN training framework (called COMET) that leverages error-bounded lossy compression to significantly reduce the memory requirement for training, to allow training larger models or to accelerate training.
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
The first challenge is to determine what parameters to share across tasks to optimize for both memory efficiency and task accuracy.
Rethinking Hard-Parameter Sharing in Multi-Domain Learning
One common sharing practice is to share the bottom layers of a deep neural network among domains while using separate top layers for each domain.
Scalable Graph Neural Network Training: The Case for Sampling
In this paper, we review and compare the two approaches.
SID-NISM: A Self-supervised Low-light Image Enhancement Framework
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms.
Post-Training 4-bit Quantization on Embedding Tables
Continuous representations have been widely adopted in recommender systems where a large number of entities are represented using embedding vectors.
In-Place Zero-Space Memory Protection for CNN
Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reliability of inference results in the presence of possible memory faults.
First Study on Data Readiness Level
We introduce the idea of Data Readiness Level (DRL) to measure the relative richness of data to answer specific questions often encountered by data scientists.
