47 citations · 87 across the 16 of their papers we have counts for
12 papers · 1 filter
Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning
Lijun Zhang, Xiao Liu, Kaleel Mahmood +2
Visual content understanding frequently relies on multi-task models to extract robust representations of a single visual input for multiple downstream tasks. However, in comparison…
Structured Pruning for Multi-Task Deep Neural Networks
Siddhant Garg, Lijun Zhang, Hui Guan
Although multi-task deep neural network (DNN) models have computation and storage benefits over individual single-task DNN models, they can be further optimized via model compressi…
Automatically Marginalized MCMC in Probabilistic Programming
Jinlin Lai, Javier Burroni, Hui Guan +1
Hamiltonian Monte Carlo (HMC) is a powerful algorithm to sample latent variables from Bayesian models. The advent of probabilistic programming languages (PPLs) frees users from wri…
Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing
Kunjal Panchal, Sunav Choudhary, Nisarg Parikh +2
Personalization in Federated Learning (FL) aims to modify a collaboratively trained global model according to each client. Current approaches to personalization in FL are at a coar…
Uplifting Message Passing Neural Network with Graph Original Information
Xiao Liu, Lijun Zhang, Hui Guan
Message passing neural networks (MPNNs) learn the representation of graph-structured data based on graph original information, including node features and graph structures, and hav…
Improving Subgraph Representation Learning via Multi-View Augmentation
Yili Shen, Xiao Liu, Cheng-Wei Ju +4
Subgraph representation learning based on Graph Neural Network (GNN) has exhibited broad applications in scientific advancements, such as predictions of molecular structure-propert…
A Tree-Structured Multi-Task Model Recommender
Lijun Zhang, Xiao Liu, Hui Guan
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL). The major challenge is to determine…
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
Lijun Zhang, Xiao Liu, Hui Guan
Multi-task learning (MTL) jointly learns a set of tasks by sharing parameters among tasks. It is a promising approach for reducing storage costs while improving task accuracy for m…
Rethinking Hard-Parameter Sharing in Multi-Domain Learning
Lijun Zhang, Qizheng Yang, Xiao Liu +1
Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sh…
Scalable Graph Neural Network Training: The Case for Sampling
Marco Serafini, Hui Guan
Graph Neural Networks (GNNs) are a new and increasingly popular family of deep neural network architectures to perform learning on graphs. Training them efficiently is challenging…
Post-Training 4-bit Quantization on Embedding Tables
Hui Guan, Andrey Malevich, Jiyan Yang +2
Continuous representations have been widely adopted in recommender systems where a large number of entities are represented using embedding vectors. As the cardinality of the entit…
In-Place Zero-Space Memory Protection for CNN
Hui Guan, Lin Ning, Zhen Lin +3
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 reli…