By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data. In this paper, we study two algorithms for this purpose, i.e., DP-SGD and DP-NSGD, which first clip or normalize \textit{per-sample} gradients to bound the sensitivity and then add noise to obfuscate the exact information. We analyze the convergence behavior of these two algorithms in the non-convex optimization setting with two common assumptions and achieve a rate $\mathcal{O}\left(\sqrt[4]{\frac{d\log(1/\delta)}{N^2\epsilon^2}}\right)$ of the gradient norm for a $d$-dimensional model, $N$ samples and $(\epsilon,\delta)$-DP, which improves over previous bounds under much weaker assumptions. Specifically, we introduce a regularizing factor in DP-NSGD and show that it is crucial in the convergence proof and subtly controls the bias and noise trade-off. Our proof deliberately handles the per-sample gradient clipping and normalization that are specified for the private setting. Empirically, we demonstrate that these two algorithms achieve similar best accuracy while DP-NSGD is comparatively easier to tune than DP-SGD and hence may help further save the privacy budget when accounting the tuning effort.
Drug-Target Affinity (DTA) prediction is an essential task for drug discovery and pharmaceutical research. Accurate predictions of DTA can greatly benefit the design of new drug. As wet experiments are costly and time consuming, the supervised data for DTA prediction is extremely limited. This seriously hinders the application of deep learning based methods, which require a large scale of supervised data. To address this challenge and improve the DTA prediction accuracy, we propose a framework with several simple yet effective strategies in this work: (1) a multi-task training strategy, which takes the DTA prediction and the masked language modeling (MLM) task on the paired drug-target dataset; (2) a semi-supervised training method to empower the drug and target representation learning by leveraging large-scale unpaired molecules and proteins in training, which differs from previous pre-training and fine-tuning methods that only utilize molecules or proteins in pre-training; and (3) a cross-attention module to enhance the interaction between drug and target representation. Extensive experiments are conducted on three real-world benchmark datasets: BindingDB, DAVIS and KIBA. The results show that our framework significantly outperforms existing methods and achieves state-of-the-art performances, e.g., $0.712$ RMSE on BindingDB IC$_{50}$ measurement with more than $5\%$ improvement than previous best work. In addition, case studies on specific drug-target binding activities, drug feature visualizations, and real-world applications demonstrate the great potential of our work. The code and data are released at https://github.com/QizhiPei/SMT-DTA
Navier-Stokes equations are significant partial differential equations that describe the motion of fluids such as liquids and air. Due to the importance of Navier-Stokes equations, the development on efficient numerical schemes is important for both science and engineer. Recently, with the development of AI techniques, several approaches have been designed to integrate deep neural networks in simulating and inferring the fluid dynamics governed by incompressible Navier-Stokes equations, which can accelerate the simulation or inferring process in a mesh-free and differentiable way. In this paper, we point out that the capability of existing deep Navier-Stokes informed methods is limited to handle non-smooth or fractional equations, which are two critical situations in reality. To this end, we propose the \emph{Deep Random Vortex Method} (DRVM), which combines the neural network with a random vortex dynamics system equivalent to the Navier-Stokes equation. Specifically, the random vortex dynamics motivates a Monte Carlo based loss function for training the neural network, which avoids the calculation of derivatives through auto-differentiation. Therefore, DRVM not only can efficiently solve Navier-Stokes equations involving rough path, non-differentiable initial conditions and fractional operators, but also inherits the mesh-free and differentiable benefits of the deep-learning-based solver. We conduct experiments on the Cauchy problem, parametric solver learning, and the inverse problem of both 2-d and 3-d incompressible Navier-Stokes equations. The proposed method achieves accurate results for simulation and inference of Navier-Stokes equations. Especially for the cases that include singular initial conditions, DRVM significantly outperforms existing PINN method.
Neural operators, as a powerful approximation to the non-linear operators between infinite-dimensional function spaces, have proved to be promising in accelerating the solution of partial differential equations (PDE). However, it requires a large amount of simulated data which can be costly to collect, resulting in a chicken-egg dilemma and limiting its usage in solving PDEs. To jump out of the dilemma, we propose a general data-free paradigm where the neural network directly learns physics from the mean squared residual (MSR) loss constructed by the discretized PDE. We investigate the physical information in the MSR loss and identify the challenge that the neural network must have the capacity to model the long range entanglements in the spatial domain of the PDE, whose patterns vary in different PDEs. Therefore, we propose the low-rank decomposition network (LordNet) which is tunable and also efficient to model various entanglements. Specifically, LordNet learns a low-rank approximation to the global entanglements with simple fully connected layers, which extracts the dominant pattern with reduced computational cost. The experiments on solving Poisson's equation and Navier-Stokes equation demonstrate that the physical constraints by the MSR loss can lead to better accuracy and generalization ability of the neural network. In addition, LordNet outperforms other modern neural network architectures in both PDEs with the fewest parameters and the fastest inference speed. For Navier-Stokes equation, the learned operator is over 50 times faster than the finite difference solution with the same computational resources.
Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all datapoints in the dataset. We propose an efficient algorithm to compute per-instance privacy guarantees for individual examples when running DP-SGD. We use our algorithm to investigate per-instance privacy losses across a number of datasets. We find that most examples enjoy stronger privacy guarantees than the worst-case bounds. We further discover that the loss and the privacy loss on an example are well-correlated. This implies groups that are underserved in terms of model utility are simultaneously underserved in terms of privacy loss. For example, on CIFAR-10, the average $\epsilon$ of the class with the highest loss (Cat) is 32% higher than that of the class with the lowest loss (Ship). We also run membership inference attacks to show this reflects disparate empirical privacy risks.
Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing them from mono audio has attracted increasing attention. This synthesis process involves not only the basic physical warping of the mono audio, but also room reverberations and head/ear related filtrations, which, however, are difficult to accurately simulate in traditional digital signal processing. In this paper, we formulate the synthesis process from a different perspective by decomposing the binaural audio into a common part that shared by the left and right channels as well as a specific part that differs in each channel. Accordingly, we propose BinauralGrad, a novel two-stage framework equipped with diffusion models to synthesize them respectively. Specifically, in the first stage, the common information of the binaural audio is generated with a single-channel diffusion model conditioned on the mono audio, based on which the binaural audio is generated by a two-channel diffusion model in the second stage. Combining this novel perspective of two-stage synthesis with advanced generative models (i.e., the diffusion models),the proposed BinauralGrad is able to generate accurate and high-fidelity binaural audio samples. Experiment results show that on a benchmark dataset, BinauralGrad outperforms the existing baselines by a large margin in terms of both object and subject evaluation metrics (Wave L2: 0.128 vs. 0.157, MOS: 3.80 vs. 3.61). The generated audio samples are available online.
Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based Transformers is largely unexplored. In this work, we mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. One may naturally assume the answer is in the affirmative -- RPE-based Transformers are universal function approximators. However, we present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. One key reason lies in that most RPEs are placed in the softmax attention that always generates a right stochastic matrix. This restricts the network from capturing positional information in the RPEs and limits its capacity. To overcome the problem and make the model more powerful, we first present sufficient conditions for RPE-based Transformers to achieve universal function approximation. With the theoretical guidance, we develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions. Therefore, the corresponding URPE-based Transformers become universal function approximators. Extensive experiments covering typical architectures and tasks demonstrate that our model is parameter-efficient and can achieve superior performance to strong baselines in a wide range of applications.
We propose a new learning framework that captures the tiered structure of many real-world user-interaction applications, where the users can be divided into two groups based on their different tolerance on exploration risks and should be treated separately. In this setting, we simultaneously maintain two policies $\pi^{\text{O}}$ and $\pi^{\text{E}}$: $\pi^{\text{O}}$ ("O" for "online") interacts with more risk-tolerant users from the first tier and minimizes regret by balancing exploration and exploitation as usual, while $\pi^{\text{E}}$ ("E" for "exploit") exclusively focuses on exploitation for risk-averse users from the second tier utilizing the data collected so far. An important question is whether such a separation yields advantages over the standard online setting (i.e., $\pi^{\text{E}}=\pi^{\text{O}}$) for the risk-averse users. We individually consider the gap-independent vs.~gap-dependent settings. For the former, we prove that the separation is indeed not beneficial from a minimax perspective. For the latter, we show that if choosing Pessimistic Value Iteration as the exploitation algorithm to produce $\pi^{\text{E}}$, we can achieve a constant regret for risk-averse users independent of the number of episodes $K$, which is in sharp contrast to the $\Omega(\log K)$ regret for any online RL algorithms in the same setting, while the regret of $\pi^{\text{O}}$ (almost) maintains its online regret optimality and does not need to compromise for the success of $\pi^{\text{E}}$.
Text to speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality, how to define/judge that quality and how to achieve it. In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset. Specifically, we leverage a variational autoencoder (VAE) for end-to-end text to waveform generation, with several key modules to enhance the capacity of the prior from text and reduce the complexity of the posterior from speech, including phoneme pre-training, differentiable duration modeling, bidirectional prior/posterior modeling, and a memory mechanism in VAE. Experiment evaluations on popular LJSpeech dataset show that our proposed NaturalSpeech achieves -0.01 CMOS (comparative mean opinion score) to human recordings at the sentence level, with Wilcoxon signed rank test at p-level p >> 0.05, which demonstrates no statistically significant difference from human recordings for the first time on this dataset.
We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. Originated in ELECTRA, this training strategy has demonstrated sample-efficiency to pretrain models at the scale of hundreds of millions of parameters. In this work, we conduct a comprehensive empirical study, and propose a recipe, namely "Model generated dEnoising TRaining Objective" (METRO), which incorporates some of the best modeling techniques developed recently to speed up, stabilize, and enhance pretrained language models without compromising model effectiveness. The resultant models, METRO-LM, consisting of up to 5.4 billion parameters, achieve new state-of-the-art on the GLUE, SuperGLUE, and SQuAD benchmarks. More importantly, METRO-LM are efficient in that they often outperform previous large models with significantly smaller model sizes and lower pretraining cost.