49 citations · 408 across the 42 of their papers we have counts for
42 papers
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
Yiwei Lu, Gautam Kamath, Yaoliang Yu
Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks…
DP-VAE: Differentially Private Pre-trained Variational Autoencoders
Dihong Jiang, Guojun Zhang, Mahdi Karami +3
Modern machine learning systems achieve great success when trained on large datasets. However, these datasets usually contain sensitive information (e.g. medical records, face imag…
Building an Efficiency Pipeline: Commutativity and Cumulativeness of Efficiency Operators for Transformers
Ji Xin, Raphael Tang, Zhiying Jiang +2
There exists a wide variety of efficiency methods for natural language processing (NLP) tasks, such as pruning, distillation, dynamic inference, quantization, etc. We can consider…
Towards Explanation for Unsupervised Graph-Level Representation Learning
Qinghua Zheng, Jihong Wang, Minnan Luo +4
Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the inpu…
Mitigating Data Heterogeneity in Federated Learning with Data Augmentation
Artur Back de Luca, Guojun Zhang, Xi Chen +1
Federated Learning (FL) is a prominent framework that enables training a centralized model while securing user privacy by fusing local, decentralized models. In this setting, one m…
Indiscriminate Data Poisoning Attacks on Neural Networks
Yiwei Lu, Gautam Kamath, Yaoliang Yu
Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention…
Proportional Fairness in Federated Learning
Guojun Zhang, Saber Malekmohammadi, Xi Chen +1
With the increasingly broad deployment of federated learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i.e. reasonably satisfactory p…
Demystifying and Generalizing BinaryConnect
Tim Dockhorn, Yaoliang Yu, Eyyüb Sari +2
BinaryConnect (BC) and its many variations have become the de facto standard for neural network quantization. However, our understanding of the inner workings of BC is still quite…
An Operator Splitting View of Federated Learning
Saber Malekmohammadi, Kiarash Shaloudegi, Zeou Hu +1
Over the past few years, the federated learning () community has witnessed a proliferation of new algorithms. However, our understating of the theory of…
: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
Xinlin Li, Bang Liu, Yaoliang Yu +3
Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast a…
Quantifying and Improving Transferability in Domain Generalization
Guojun Zhang, Han Zhao, Yaoliang Yu +1
Out-of-distribution generalization is one of the key challenges when transferring a model from the lab to the real world. Existing efforts mostly focus on building invariant featur…
Posterior Differential Regularization with f-divergence for Improving Model Robustness
Hao Cheng, Xiaodong Liu, Lis Pereira +2
We address the problem of enhancing model robustness through regularization. Specifically, we focus on methods that regularize the model posterior difference between clean and nois…
OLALA: Object-Level Active Learning for Efficient Document Layout Annotation
Zejiang Shen, Jian Zhao, Melissa Dell +2
Document images often have intricate layout structures, with numerous content regions (e.g. texts, figures, tables) densely arranged on each page. This makes the manual annotation…
Stronger and Faster Wasserstein Adversarial Attacks
Kaiwen Wu, Allen Houze Wang, Yaoliang Yu
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to "small, imperceptible" perturbations known as adversarial attacks. While the majority of ex…
Density Deconvolution with Normalizing Flows
Tim Dockhorn, James A. Ritchie, Yaoliang Yu +1
Density deconvolution is the task of estimating a probability density function given only noise-corrupted samples. We can fit a Gaussian mixture model to the underlying density by…
Newton-type Methods for Minimax Optimization
Guojun Zhang, Kaiwen Wu, Pascal Poupart +1
Differential games, in particular two-player sequential zero-sum games (a.k.a. minimax optimization), have been an important modeling tool in applied science and received renewed i…
Federated Learning Meets Multi-objective Optimization
Zeou Hu, Kiarash Shaloudegi, Guojun Zhang +1
Federated learning has emerged as a promising, massively distributed way to train a joint deep model over large amounts of edge devices while keeping private user data strictly on…
Network Comparison with Interpretable Contrastive Network Representation Learning
Takanori Fujiwara, Jian Zhao, Francine Chen +2
Identifying unique characteristics in a network through comparison with another network is an essential network analysis task. For example, with networks of protein interactions ob…
Showing Your Work Doesn't Always Work
Raphael Tang, Jaejun Lee, Ji Xin +3
In natural language processing, a recently popular line of work explores how to best report the experimental results of neural networks. One exemplar publication, titled "Show Your…
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
Ji Xin, Raphael Tang, Jaejun Lee +2
Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which…
Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space
Yingyi Ma, Vignesh Ganapathiraman, Yaoliang Yu +1
Invariance (defined in a general sense) has been one of the most effective priors for representation learning. Direct factorization of parametric models is feasible only for a smal…
A Positivstellensatz for Conditional SAGE Signomials
Allen Houze Wang, Priyank Jaini, Yaoliang Yu +1
Recently, the conditional SAGE certificate has been proposed as a sufficient condition for signomial positivity over a convex set. In this article, we show that the conditional SAG…
Optimality and Stability in Non-Convex Smooth Games
Guojun Zhang, Pascal Poupart, Yaoliang Yu
Convergence to a saddle point for convex-concave functions has been studied for decades, while recent years has seen a surge of interest in non-convex (zero-sum) smooth games, moti…
Unsupervised Multilingual Alignment using Wasserstein Barycenter
Xin Lian, Kshitij Jain, Jakub Truszkowski +2
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is t…