Yulai Cong

Yulai Cong

Cooperation plays a pivotal role in the evolution of human intelligence; moreover, it also underlies the recent revolutionary advancement of artificial intelligence (AI) that is driven by foundation models. Specifically, we reveal that the training of foundation models can be interpreted as a form of big cooperative learning (\textit{abbr.} big learning), where massive learning individuals/tasks \emph{cooperate} to approach the unique essence of data from diverse perspectives of data prediction, leveraging a universal model. The presented big learning therefore unifies most training objectives of foundation models within a consistent framework, where their underlying assumptions are exposed simultaneously. We design tailored simulations to demonstrate the principle of big learning, based on which we provide learning-perspective justifications for the successes of foundation models, with interesting side-products. Furthermore, we reveal that big learning is a new dimension for upgrading conventional machine learning paradigms, valuable for endowing reinvigorations to associated applications; as an illustrative example, we propose the BigLearn-GAN, which is a novel adversarially-trained foundation model with versatile data sampling capabilities. Code is available at \texttt{https://github.com/YulaiCong/BigCooperativeLearning}.

Yulai Cong, Miaoyun Zhao

Recent advances in big/foundation models reveal a promising path for deep learning, where the roadmap steadily moves from big data to big models to (the newly-introduced) big learning. Specifically, the big learning exhaustively exploits the information inherent in its large-scale complete/incomplete training data, by simultaneously modeling many/all joint/conditional/marginal data distributions across potentially diverse domains, with one universal foundation model. We reveal that big learning ($i$) underlies most existing foundation models, ($ii$) is equipped with extraordinary flexibilities for complete/incomplete training data and trustworthy data tasks, ($iii$) is capable of delivering all joint/conditional/marginal data capabilities with one universal model, and ($iv$) unifies conventional machine learning paradigms and enables their flexible cooperations, manifested as a universal learning paradigm. Diverse experiments are carried out to validate the effectiveness of the presented big learning.

Yulai Cong, Sijia Li

Mixture models serve as one fundamental tool with versatile applications. However, their training techniques, like the popular Expectation Maximization (EM) algorithm, are notoriously sensitive to parameter initialization and often suffer from bad local optima that could be arbitrarily worse than the optimal. To address the long-lasting bad-local-optima challenge, we draw inspiration from the recent ground-breaking foundation models and propose to leverage their underlying big learning principle to upgrade the EM. Specifically, we present the Big Learning EM (BigLearn-EM), an EM upgrade that simultaneously performs joint, marginal, and orthogonally transformed marginal matchings between data and model distributions. Through simulated experiments, we empirically show that the BigLearn-EM is capable of delivering the optimal with high probability; comparisons on benchmark clustering datasets further demonstrate its effectiveness and advantages over existing techniques. The code is available at https://github.com/YulaiCong/Big-Learning-Expectation-Maximization.

Yulai Cong, Miaoyun Zhao, Jianqiao Li et al.

As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected. Motivated by that, we propose a GAN memory for lifelong learning, which is capable of remembering a stream of datasets via generative processes, with \emph{no} forgetting. Our GAN memory is based on recognizing that one can modulate the "style" of a GAN model to form perceptually-distant targeted generation. Accordingly, we propose to do sequential style modulations atop a well-behaved base GAN model, to form sequential targeted generative models, while simultaneously benefiting from the transferred base knowledge. The GAN memory -- that is motivated by lifelong learning -- is therefore itself manifested by a form of lifelong learning, via forward transfer and modulation of information from prior tasks. Experiments demonstrate the superiority of our method over existing approaches and its effectiveness in alleviating catastrophic forgetting for lifelong classification problems. Code is available at https://github.com/MiaoyunZhao/GANmemory_LifelongLearning.

Miaoyun Zhao, Yulai Cong, Shuyang Dai et al.

Maximum likelihood (ML) and adversarial learning are two popular approaches for training generative models, and from many perspectives these techniques are complementary. ML learning encourages the capture of all data modes, and it is typically characterized by stable training. However, ML learning tends to distribute probability mass diffusely over the data space, $e.g.$, yielding blurry synthetic images. Adversarial learning is well known to synthesize highly realistic natural images, despite practical challenges like mode dropping and delicate training. We propose an $α$-Bridge to unify the advantages of ML and adversarial learning, enabling the smooth transfer from one to the other via the $α$-divergence. We reveal that generalizations of the $α$-Bridge are closely related to approaches developed recently to regularize adversarial learning, providing insights into that prior work, and further understanding of why the $α$-Bridge performs well in practice.

Yulai Cong, Miaoyun Zhao, Jianqiao Li et al.

An unbiased low-variance gradient estimator, termed GO gradient, was proposed recently for expectation-based objectives $\mathbb{E}_{q_{\boldsymbolγ}(\boldsymbol{y})} [f(\boldsymbol{y})]$, where the random variable (RV) $\boldsymbol{y}$ may be drawn from a stochastic computation graph with continuous (non-reparameterizable) internal nodes and continuous/discrete leaves. Upgrading the GO gradient, we present for $\mathbb{E}_{q_{\boldsymbol{\boldsymbolγ}}(\boldsymbol{y})} [f(\boldsymbol{y})]$ an unbiased low-variance Hessian estimator, named GO Hessian. Considering practical implementation, we reveal that GO Hessian is easy-to-use with auto-differentiation and Hessian-vector products, enabling efficient cheap exploitation of curvature information over stochastic computation graphs. As representative examples, we present the GO Hessian for non-reparameterizable gamma and negative binomial RVs/nodes. Based on the GO Hessian, we design a new second-order method for $\mathbb{E}_{q_{\boldsymbol{\boldsymbolγ}}(\boldsymbol{y})} [f(\boldsymbol{y})]$, with rigorous experiments conducted to verify its effectiveness and efficiency.

Hao Zhang, Bo Chen, Yulai Cong et al.

To build a flexible and interpretable model for document analysis, we develop deep autoencoding topic model (DATM) that uses a hierarchy of gamma distributions to construct its multi-stochastic-layer generative network. In order to provide scalable posterior inference for the parameters of the generative network, we develop topic-layer-adaptive stochastic gradient Riemannian MCMC that jointly learns simplex-constrained global parameters across all layers and topics, with topic and layer specific learning rates. Given a posterior sample of the global parameters, in order to efficiently infer the local latent representations of a document under DATM across all stochastic layers, we propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a Weibull distribution based stochastic downward generative model. To jointly model documents and their associated labels, we further propose supervised DATM that enhances the discriminative power of its latent representations. The efficacy and scalability of our models are demonstrated on both unsupervised and supervised learning tasks on big corpora.

Miaoyun Zhao, Yulai Cong, Lawrence Carin

Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting potential for augmenting training sets with GAN-generated data. While this scenario is of particular relevance when there are limited data available, there is still the issue of training the GAN itself based on that limited data. To facilitate this, we leverage existing GAN models pretrained on large-scale datasets (like ImageNet) to introduce additional knowledge (which may not exist within the limited data), following the concept of transfer learning. Demonstrated by natural-image generation, we reveal that low-level filters (those close to observations) of both the generator and discriminator of pretrained GANs can be transferred to facilitate generation in a perceptually-distinct target domain with limited training data. To further adapt the transferred filters to the target domain, we propose adaptive filter modulation (AdaFM). An extensive set of experiments is presented to demonstrate the effectiveness of the proposed techniques on generation with limited data.

Yulai Cong, Miaoyun Zhao, Ke Bai et al.

Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$. Most existing methods either (i) suffer from high variance, seeking help from (often) complicated variance-reduction techniques; or (ii) they only apply to reparameterizable continuous random variables and employ a reparameterization trick. To address these limitations, we propose a General and One-sample (GO) gradient that (i) applies to many distributions associated with non-reparameterizable continuous or discrete random variables, and (ii) has the same low-variance as the reparameterization trick. We find that the GO gradient often works well in practice based on only one Monte Carlo sample (although one can of course use more samples if desired). Alongside the GO gradient, we develop a means of propagating the chain rule through distributions, yielding statistical back-propagation, coupling neural networks to common random variables.

Yulai Cong, Bo Chen, Hongwei Liu et al.

It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers. For the Poisson gamma belief network (PGBN), a recently proposed deep discrete LVM, we derive an alternative representation that is referred to as deep latent Dirichlet allocation (DLDA). Exploiting data augmentation and marginalization techniques, we derive a block-diagonal Fisher information matrix and its inverse for the simplex-constrained global model parameters of DLDA. Exploiting that Fisher information matrix with stochastic gradient MCMC, we present topic-layer-adaptive stochastic gradient Riemannian (TLASGR) MCMC that jointly learns simplex-constrained global parameters across all layers and topics, with topic and layer specific learning rates. State-of-the-art results are demonstrated on big data sets.

Mingyuan Zhou, Yulai Cong, Bo Chen

To infer multilayer deep representations of high-dimensional discrete and nonnegative real vectors, we propose an augmentable gamma belief network (GBN) that factorizes each of its hidden layers into the product of a sparse connection weight matrix and the nonnegative real hidden units of the next layer. The GBN's hidden layers are jointly trained with an upward-downward Gibbs sampler that solves each layer with the same subroutine. The gamma-negative binomial process combined with a layer-wise training strategy allows inferring the width of each layer given a fixed budget on the width of the first layer. Example results illustrate interesting relationships between the width of the first layer and the inferred network structure, and demonstrate that the GBN can add more layers to improve its performance in both unsupervisedly extracting features and predicting heldout data. For exploratory data analysis, we extract trees and subnetworks from the learned deep network to visualize how the very specific factors discovered at the first hidden layer and the increasingly more general factors discovered at deeper hidden layers are related to each other, and we generate synthetic data by propagating random variables through the deep network from the top hidden layer back to the bottom data layer.

Mingyuan Zhou, Yulai Cong, Bo Chen

To infer a multilayer representation of high-dimensional count vectors, we propose the Poisson gamma belief network (PGBN) that factorizes each of its layers into the product of a connection weight matrix and the nonnegative real hidden units of the next layer. The PGBN's hidden layers are jointly trained with an upward-downward Gibbs sampler, each iteration of which upward samples Dirichlet distributed connection weight vectors starting from the first layer (bottom data layer), and then downward samples gamma distributed hidden units starting from the top hidden layer. The gamma-negative binomial process combined with a layer-wise training strategy allows the PGBN to infer the width of each layer given a fixed budget on the width of the first layer. The PGBN with a single hidden layer reduces to Poisson factor analysis. Example results on text analysis illustrate interesting relationships between the width of the first layer and the inferred network structure, and demonstrate that the PGBN, whose hidden units are imposed with correlated gamma priors, can add more layers to increase its performance gains over Poisson factor analysis, given the same limit on the width of the first layer.