Search Results for author:
Found 28 papers, 12 papers with code
Posterior Differential Regularization with f-divergence for Improving Model Robustness
Theoretically, we provide a connection of two recent methods, Jacobian Regularization and Virtual Adversarial Training, under this framework.
Quantifying and Improving Transferability in Domain Generalization
We then prove that our transferability can be estimated with enough samples and give a new upper bound for the target error based on our transferability.
$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy efficient compared to conventional neural networks.
Towards Explanation for Unsupervised Graph-Level Representation Learning
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 input graph is the most crucial to decide the model's decision?}"
OLALA: Object-Level Active Learning for Efficient Document Layout Annotation
Document images often have intricate layout structures, with numerous content regions (e. g. texts, figures, tables) densely arranged on each page.
BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression
The slow speed of BERT has motivated much research on accelerating its inference, and the early exiting idea has been proposed to make trade-offs between model quality and efficiency.
Proportional Fairness in Federated Learning
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 performances for each of the numerous diverse clients.
Mitigating Data Heterogeneity in Federated Learning with Data Augmentation
Federated Learning (FL) is a prominent framework that enables training a centralized model while securing user privacy by fusing local, decentralized models.
Early Exiting BERT for Efficient Document Ranking
Pre-trained language models such as BERT have shown their effectiveness in various tasks.
The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing
To fill this void in the literature, we study in this paper selective prediction for NLP, comparing different models and confidence estimators.
Indiscriminate Data Poisoning Attacks on Neural Networks
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.
Efficient Structured Matrix Rank Minimization
We study the problem of finding structured low-rank matrices using nuclear norm regularization where the structure is encoded by a linear map.
An Operator Splitting View of Federated Learning
Over the past few years, the federated learning ($\texttt{FL}$) community has witnessed a proliferation of new $\texttt{FL}$ algorithms.
Conditional Generative Quantile Networks via Optimal Transport and Convex Potentials
Quantile regression has a natural extension to generative modelling by leveraging a stronger convergence in pointwise rather than in distribution.
$f$-Mutual Information Contrastive Learning
Self-supervised contrastive learning is an emerging field due to its power in providing good data representations.
Revisiting flow generative models for Out-of-distribution detection
Deep generative models have been widely used in practical applications such as the detection of out-of-distribution (OOD) data.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Demystifying and Generalizing BinaryConnect
BinaryConnect (BC) and its many variations have become the de facto standard for neural network quantization.
Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training
Our study of 22 mitigation techniques and five baselines reveals up to 12. 6% fairness variance across identical training runs with identical seeds.
S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy-efficient compared to conventional neural networks.
Building an Efficiency Pipeline: Commutativity and Cumulativeness of Efficiency Operators for Transformers
There exists a wide variety of efficiency methods for natural language processing (NLP) tasks, such as pruning, distillation, dynamic inference, quantization, etc.
DP$^2$-VAE: Differentially Private Pre-trained Variational Autoencoders
Similar to other differentially private (DP) learners, the major challenge for DPGM is also how to achieve a subtle balance between utility and privacy.
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
Building on existing parameter corruption attacks and refining the Gradient Canceling attack, we perform extensive experiments to confirm our theoretical findings, test the predictability of our transition threshold, and significantly improve existing indiscriminate data poisoning baselines over a range of datasets and models.
$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning
In self-supervised contrastive learning, a widely-adopted objective function is InfoNCE, which uses the heuristic cosine similarity for the representation comparison, and is closely related to maximizing the Kullback-Leibler (KL)-based mutual information.
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors
In this paper, we extend the exploration of the threat of indiscriminate attacks on downstream tasks that apply pre-trained feature extractors.
Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
In neural network binarization, BinaryConnect (BC) and its variants are considered the standard.
Structure Preserving Diffusion Models
Diffusion models have become the leading distribution-learning method in recent years.
Disguised Copyright Infringement of Latent Diffusion Models
Copyright infringement may occur when a generative model produces samples substantially similar to some copyrighted data that it had access to during the training phase.
Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games
Our algorithm simultaneously achieves a Nash regret and a regret bound of $O(T^{4/5})$ for potential games, which matches the best available result, without using additional projection steps.
