121 citations · 211 across the 15 of their papers we have counts for
16 papers
A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space
Zhangyu Wang, Lantian Xu, Zhifeng Kong +3
Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph. However, in practice, lea…
Data Redaction from Conditional Generative Models
Zhifeng Kong, Kamalika Chaudhuri
Deep generative models are known to produce undesirable samples such as harmful content. Traditional mitigation methods include re-training from scratch, filtering, or editing; how…
Can Membership Inferencing be Refuted?
Zhifeng Kong, Amrita Roy Chowdhury, Kamalika Chaudhuri
Membership inference (MI) attack is currently the most popular test for measuring privacy leakage in machine learning models. Given a machine learning model, a data point and some…
Approximate Data Deletion in Generative Models
Zhifeng Kong, Scott Alfeld
Users have the right to have their data deleted by third-party learned systems, as codified by recent legislation such as the General Data Protection Regulation (GDPR) and the Cali…
Data Redaction from Pre-trained GANs
Zhifeng Kong, Kamalika Chaudhuri
Large pre-trained generative models are known to occasionally output undesirable samples, which undermines their trustworthiness. The common way to mitigate this is to re-train the…
Speech Denoising in the Waveform Domain with Self-Attention
Zhifeng Kong, Wei Ping, Ambrish Dantrey +1
In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-a…
A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
Zhaoyang Lyu, Zhifeng Kong, Xudong Xu +2
3D point cloud is an important 3D representation for capturing real world 3D objects. However, real-scanned 3D point clouds are often incomplete, and it is important to recover com…
On Fast Sampling of Diffusion Probabilistic Models
Zhifeng Kong, Wei Ping
In this work, we propose FastDPM, a unified framework for fast sampling in diffusion probabilistic models. FastDPM generalizes previous methods and gives rise to new algorithms wit…
Understanding Instance-based Interpretability of Variational Auto-Encoders
Zhifeng Kong, Kamalika Chaudhuri
Instance-based interpretation methods have been widely studied for supervised learning methods as they help explain how black box neural networks predict. However, instance-based i…
Universal Approximation of Residual Flows in Maximum Mean Discrepancy
Zhifeng Kong, Kamalika Chaudhuri
Normalizing flows are a class of flexible deep generative models that offer easy likelihood computation. Despite their empirical success, there is little theoretical understanding…
DiffWave: A Versatile Diffusion Model for Audio Synthesis
Zhifeng Kong, Wei Ping, Jiaji Huang +2
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts th…
The Expressive Power of a Class of Normalizing Flow Models
Zhifeng Kong, Kamalika Chaudhuri
Normalizing flows have received a great deal of recent attention as they allow flexible generative modeling as well as easy likelihood computation. While a wide variety of flow mod…
Fastened CROWN: Tightened Neural Network Robustness Certificates
Zhaoyang Lyu, Ching-Yun Ko, Zhifeng Kong +3
The rapid growth of deep learning applications in real life is accompanied by severe safety concerns. To mitigate this uneasy phenomenon, much research has been done providing reli…
Convergence Analysis of the Dynamics of a Special Kind of Two-Layered Neural Networks with and Regularization
Zhifeng Kong
In this paper, we made an extension to the convergence analysis of the dynamics of two-layered bias-free networks with one output. We took into consideration two popular reg…
WristAuthen: A Dynamic Time Wrapping Approach for User Authentication by Hand-Interaction through Wrist-Worn Devices
Qi Lyu, Zhifeng Kong, Chao Shen +1
The growing trend of using wearable devices for context-aware computing and pervasive sensing systems has raised its potentials for quick and reliable authentication techniques. Si…
Generative Adversarial Networks with Inverse Transformation Unit
Zhifeng Kong, Shuo Ding
In this paper we introduce a new structure to Generative Adversarial Networks by adding an inverse transformation unit behind the generator. We present two theorems to claim the co…