Author name cluster

Wenlin Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

2 author rows

EAAI Journal 2025 Journal Article

PDFusion: A domain-adaptive incremental learning model based on Physical-Data Fusion for lithium-ion battery state estimation

Yufei Xie
Wenlin Wang
Guohua Wu
Haichuan Zhang

Accurate estimation of battery state is crucial for ensuring the safe, stable, and efficient operation of lithium-ion batteries. State of Charge (SOC) and State of Energy (SOE) are critical parameters for assessing battery health, but accurately estimating them remains challenging due to the nonlinear, non-stationary and strong coupling characteristics of complex battery charging and discharging processes. To address these issues, a novel domain-adaptive incremental learning model driven by both physical and data is proposed. To reduce state noise and covariance, a novel Kalman Filtering method is used for primary trend prediction. However, physics-based models fail to estimate the seasonal components that contain time-frequency patterns. To overcome the limitation, a data-driven model with Time-frequency Interactive Attention (TIA) is proposed to accurately capture the temporal relationships and effectively compensate for peak errors. To make the model operate across different temperature conditions, a domain-adaptive incremental learning strategy is employed. The results on Lithium iron phosphate (LFP) and Nickel Cobalt Manganese (NCM) batteries show that the proposed model outperforms current state-of-the-art (SOTAs), with the average Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of 0. 048 and 0. 021 for LFP under two operating conditions, and 0. 060 and 0. 023 for NCM. Under Beijing Dynamic Stress test (BJDST) conditions, RMSE and MAE are reduced by 22. 69% and 28. 56% respectively. Under US06 Highway Driving Schedule (US06) conditions, these metrics are reduced by 41. 02% and 49. 09%, respectively. The algorithm exhibits high robustness to temperature, enabling precise estimation of the lithium-ion battery states.

Details DOI

AAAI Conference 2021 Conference Paper

Learning to Recommend from Sparse Data via Generative User Feedback

Wenlin Wang

Traditional collaborative filtering (CF) based recommender systems tend to perform poorly when the user-item interactions/ratings are highly scarce. To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback. The proposed framework consists of a “recommender” and a “virtual user”. The “recommender” is formulated as a CF model, recommending items according to observed user preference. The “virtual user” estimates rewards from the recommended items and generates a feedback in addition to the observed user preference. The “recommender” connected with the “virtual user” constructs a closed loop, that recommends users with items and imitates the unobserved feedback of the users to the recommended items. The synthetic feedback is used to augment the observed user preference and improve recommendation results. Theoretically, such model design can be interpreted as inverse reinforcement learning, which can be learned effectively via rollout (simulation). Experimental results show that the proposed framework is able to enrich the learning of user preference and boost the performance of existing collaborative filtering methods on multiple datasets.

PDF Details

AAAI Conference 2020 Conference Paper

Graph-Driven Generative Models for Heterogeneous Multi-Task Learning

Wenlin Wang
Hongteng Xu
Zhe Gan
Bai Li
Guoyin Wang
Liqun Chen
Qian Yang
Wenqi Wang

We propose a novel graph-driven generative model, that uniﬁes multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogeneous learning tasks, which correspond to different generative processes, often rely on data with a shared graph structure. Accordingly, our model combines a graph convolutional network (GCN) with multiple variational autoencoders, thus embedding the nodes of the graph (i. e. , samples for the tasks) in a uniform manner, while specializing their organization and usage to different tasks. With a focus on healthcare applications (tasks), including clinical topic modeling, procedure recommendation and admission-type prediction, we demonstrate that our method successfully leverages information across different tasks, boosting performance in all tasks and outperforming existing state-of-the-art approaches.

PDF Details

AAAI Conference 2020 Conference Paper

Sequence Generation with Optimal-Transport-Enhanced Reinforcement Learning

Liqun Chen
Ke Bai
Chenyang Tao
Yizhe Zhang
Guoyin Wang
Wenlin Wang
Ricardo Henao
Lawrence Carin

Reinforcement learning (RL) has been widely used to aid training in language generation. This is achieved by enhancing standard maximum likelihood objectives with userspeciﬁed reward functions that encourage global semantic consistency. We propose a principled approach to address the difﬁculties associated with RL-based solutions, namely, highvariance gradients, uninformative rewards and brittle training. By leveraging the optimal transport distance, we introduce a regularizer that signiﬁcantly alleviates the above issues. Our formulation emphasizes the preservation of semantic features, enabling end-to-end training instead of ad-hoc ﬁne-tuning, and when combined with RL, it controls the exploration space for more efﬁcient model updates. To validate the effectiveness of the proposed solution, we perform a comprehensive evaluation covering a wide variety of NLP tasks: machine translation, abstractive text summarization and image caption, with consistent improvements over competing solutions.

PDF Details

NeurIPS Conference 2019 Conference Paper

Certified Adversarial Robustness with Additive Noise

Bai Li
Changyou Chen
Wenlin Wang
Lawrence Carin

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning algorithm. Although a significant body of work on developing defense models has been developed, most such models are heuristic and are often vulnerable to adaptive attacks. Defensive methods that provide theoretical robustness guarantees have been studied intensively, yet most fail to obtain non-trivial robustness when a large-scale model and data are present. To address these limitations, we introduce a framework that is scalable and provides certified bounds on the norm of the input manipulation for constructing adversarial examples. We establish a connection between robustness against adversarial perturbation and additive random noise, and propose a training strategy that can significantly improve the certified bounds. Our evaluation on MNIST, CIFAR-10 and ImageNet suggests that our method is scalable to complicated models and large data sets, while providing competitive robustness to state-of-the-art provable defense methods.

PDF Details

NeurIPS Conference 2019 Conference Paper

Improving Textual Network Learning with Variational Homophilic Embeddings

Wenlin Wang
Chenyang Tao
Zhe Gan
Guoyin Wang
Liqun Chen
Xinyuan Zhang
Ruiyi Zhang
Qian Yang

The performance of many network learning applications crucially hinges on the success of network embedding algorithms, which aim to encode rich network information into low-dimensional vertex-based vector representations. This paper considers a novel variational formulation of network embeddings, with special focus on textual networks. Different from most existing methods that optimize a discriminative objective, we introduce Variational Homophilic Embedding (VHE), a fully generative model that learns network embeddings by modeling the semantic (textual) information with a variational autoencoder, while accounting for the structural (topology) information through a novel homophilic prior design. Homophilic vertex embeddings encourage similar embedding vectors for related (connected) vertices. The VHE encourages better generalization for downstream tasks, robustness to incomplete observations, and the ability to generalize to unseen vertices. Extensive experiments on real-world networks, for multiple tasks, demonstrate that the proposed method achieves consistently superior performance relative to competing state-of-the-art approaches.

PDF Details

NeurIPS Conference 2019 Conference Paper

Ouroboros: On Accelerating Training of Transformer-Based Language Models

Qian Yang
Zhouyuan Huo
Wenlin Wang
Lawrence Carin

Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model parallelism is required if a model is too large to fit in a single computing device. Current methods for model parallelism either suffer from backward locking in backpropagation or are not applicable to language models. We propose the first model-parallel algorithm that speeds the training of Transformer-based language models. We also prove that our proposed algorithm is guaranteed to converge to critical points for non-convex problems. Extensive experiments on Transformer and Transformer-XL language models demonstrate that the proposed algorithm obtains a much faster speedup beyond data parallelism, with comparable or better accuracy. Code to reproduce experiments is to be found at \url{https: //github. com/LaraQianYang/Ouroboros}.

PDF Details

UAI Conference 2018 Conference Paper

A Unified Particle-Optimization Framework for Scalable Bayesian Sampling

Changyou Chen
Ruiyi Zhang 0002
Wenlin Wang
Bai Li 0001
Liqun Chen 0001

There has been recent interest in developing scalable Bayesian sampling methods such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) for big-data analysis. A standard SG-MCMC algorithm simulates samples from a discrete-time Markov chain to approximate a target distribution, thus samples could be highly correlated, an undesired property for SG-MCMC. In contrary, SVGD directly optimizes a set of particles to approximate a target distribution, and thus is able to obtain good approximations with relatively much fewer samples. In this paper, we propose a principle particle-optimization framework based on Wasserstein gradient flows to unify SG-MCMC and SVGD, and to allow new algorithms to be developed. Our framework interprets SG-MCMC as particle optimization on the space of probability measures, revealing a strong connection between SG-MCMC and SVGD. The key component of our framework is several particle-approximate techniques to efficiently solve the original partial differential equations on the space of probability measures. Extensive experiments on both synthetic data and deep neural networks demonstrate the effectiveness and efficiency of our framework for scalable Bayesian sampling.

Details

ICML Conference 2018 Conference Paper

Continuous-Time Flows for Efficient Inference and Density Estimation

Changyou Chen
Chunyuan Li
Liquan Chen
Wenlin Wang
Yunchen Pu
Lawrence Carin

Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizing flows and generative adversarial networks (GANs), are often developed independently. In this paper, we propose the concept of continuous-time flows (CTFs), a family of diffusion-based methods that are able to asymptotically approach a target distribution. Distinct from normalizing flows and GANs, CTFs can be adopted to achieve the above two goals in one framework, with theoretical guarantees. Our framework includes distilling knowledge from a CTF for efficient inference, and learning an explicit energy-based distribution with CTFs for density estimation. Both tasks rely on a new technique for distribution matching within amortized learning. Experiments on various tasks demonstrate promising performance of the proposed CTF framework, compared to related techniques.

Details

NeurIPS Conference 2018 Conference Paper

Distilled Wasserstein Learning for Word Embedding and Topic Modeling

Hongteng Xu
Wenlin Wang
Wei Liu
Lawrence Carin

We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclidean distance between word embeddings may be employed as the underlying distance in the Wasserstein topic model. The word distributions of topics, their optimal transport to the word distributions of documents, and the embeddings of words are learned in a unified framework. When learning the topic model, we leverage a distilled ground-distance matrix to update the topic distributions and smoothly calculate the corresponding optimal transports. Such a strategy provides the updating of word embeddings with robust guidance, improving algorithm convergence. As an application, we focus on patient admission records, in which the proposed method embeds the codes of diseases and procedures and learns the topics of admissions, obtaining superior performance on clinically-meaningful disease network construction, mortality prediction as a function of admission codes, and procedure recommendation.

PDF Details

AAAI Conference 2018 Conference Paper

Zero-Shot Learning via Class-Conditioned Deep Generative Models

Wenlin Wang
Yunchen Pu
Vinay Verma
Kai Fan
Yizhe Zhang
Changyou Chen
Piyush Rai
Lawrence Carin

We present a deep generative model for Zero-Shot Learning (ZSL). Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen class using a classspeciﬁc latent-space distribution, conditioned on class attributes. We use these latent-space distributions as a prior for a supervised variational autoencoder (VAE), which also facilitates learning highly discriminative feature representations for the inputs. The entire framework is learned end-to-end using only the seen-class training data. At test time, the label for an unseen-class test input is the class that maximizes the VAE lower bound. We further extend the model to a (i) semi-supervised/transductive setting by leveraging unlabeled unseen-class data via an unsupervised learning module, and (ii) few-shot learning where we also have a small number of labeled inputs from the unseen classes. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of benchmark data sets.

PDF Details