Search Results for author: Yuyang Wang

Found 61 papers, 26 papers with code

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting

1 code implementation12 Jul 2022 Zhihan Gao, Xingjian Shi, Hao Wang, Yi Zhu, Yuyang Wang, Mu Li, Dit-yan Yeung

With the explosive growth of the spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks.

Earth Surface Forecasting Weather Forecasting

Molecular Contrastive Learning of Representations via Graph Neural Networks

1 code implementation19 Feb 2021 Yuyang Wang, Jianren Wang, Zhonglin Cao, Amir Barati Farimani

In this work, we present MolCLR: Molecular Contrastive Learning of Representations via Graph Neural Networks (GNNs), a self-supervised learning framework that leverages large unlabeled data (~10M unique molecules).

BIG-bench Machine Learning Contrastive Learning +4

PreDiff: Precipitation Nowcasting with Latent Diffusion Models

1 code implementation NeurIPS 2023 Zhihan Gao, Xingjian Shi, Boran Han, Hao Wang, Xiaoyong Jin, Danielle Maddix, Yi Zhu, Mu Li, Yuyang Wang

We conduct empirical studies on two datasets: N-body MNIST, a synthetic dataset with chaotic behavior, and SEVIR, a real-world precipitation nowcasting dataset.

Denoising

TransPolymer: a Transformer-based language model for polymer property predictions

1 code implementation3 Sep 2022 Changwen Xu, Yuyang Wang, Amir Barati Farimani

Rigorous experiments on ten polymer property prediction benchmarks demonstrate the superior performance of TransPolymer.

Language Modelling Masked Language Modeling +2

Graph-Relational Domain Adaptation

1 code implementation ICLR 2022 Zihao Xu, Hao He, Guang-He Lee, Yuyang Wang, Hao Wang

In this work, we relax such uniform alignment by using a domain graph to encode domain adjacency, e. g., a graph of states in the US with each state as a domain and each edge indicating adjacency, thereby allowing domains to align flexibly based on the graph structure.

Domain Adaptation

MOFormer: Self-Supervised Transformer model for Metal-Organic Framework Property Prediction

1 code implementation25 Oct 2022 Zhonglin Cao, Rishikesh Magar, Yuyang Wang, Amir Barati Farimani

Furthermore, we revealed that MOFormer can be more data-efficient on quantum-chemical property prediction than structure-based CGCNN when training data is limited.

Property Prediction Self-Supervised Learning

Robust Probabilistic Time Series Forecasting

1 code implementation24 Feb 2022 Taeho Yoon, Youngsuk Park, Ernest K. Ryu, Yuyang Wang

Probabilistic time series forecasting has played critical role in decision-making processes due to its capability to quantify uncertainties.

Decision Making Probabilistic Time Series Forecasting +1

Intermittent Demand Forecasting with Deep Renewal Processes

1 code implementation23 Nov 2019 Ali Caner Turkmen, Yuyang Wang, Tim Januschowski

Intermittent demand, where demand occurrences appear sporadically in time, is a common and challenging problem in forecasting.

Point Processes

Domain Adaptation for Time Series Forecasting via Attention Sharing

1 code implementation13 Feb 2021 Xiaoyong Jin, Youngsuk Park, Danielle C. Maddix, Hao Wang, Yuyang Wang

Recently, deep neural networks have gained increasing popularity in the field of time series forecasting.

Domain Adaptation Time Series +1

AugLiChem: Data Augmentation Library of Chemical Structures for Machine Learning

1 code implementation30 Nov 2021 Rishikesh Magar, Yuyang Wang, Cooper Lorsung, Chen Liang, Hariharan Ramasubramanian, Peiyuan Li, Amir Barati Farimani

Inspired by the success of data augmentations in computer vision and natural language processing, we developed AugLiChem: the data augmentation library for chemical structures.

BIG-bench Machine Learning Data Augmentation +1

First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting

1 code implementation15 Dec 2022 Xiyuan Zhang, Xiaoyong Jin, Karthick Gopalswamy, Gaurav Gupta, Youngsuk Park, Xingjian Shi, Hao Wang, Danielle C. Maddix, Yuyang Wang

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years.

Time Series Time Series Forecasting

Deep Explicit Duration Switching Models for Time Series

1 code implementation NeurIPS 2021 Abdul Fatir Ansari, Konstantinos Benidis, Richard Kurle, Ali Caner Turkmen, Harold Soh, Alexander J. Smola, Yuyang Wang, Tim Januschowski

We propose the Recurrent Explicit Duration Switching Dynamical System (RED-SDS), a flexible model that is capable of identifying both state- and time-dependent switching dynamics.

Time Series Time Series Analysis

Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems

3 code implementations20 Nov 2020 Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu

While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.

Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast

1 code implementation18 Feb 2022 Yuyang Wang, Rishikesh Magar, Chen Liang, Amir Barati Farimani

On most benchmarks, the generic GNN pre-trained by iMolCLR rivals or even surpasses supervised learning models with sophisticated architecture designs and engineered features.

Contrastive Learning Self-Supervised Learning

Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials

1 code implementation3 Mar 2023 Yuyang Wang, Changwen Xu, Zijie Li, Amir Barati Farimani

These results highlight the potential for leveraging denoise pretraining approaches to build more generalizable neural potentials for complex molecular systems.

Predicting CO$_2$ Absorption in Ionic Liquids with Molecular Descriptors and Explainable Graph Neural Networks

1 code implementation29 Sep 2022 Yue Jian, Yuyang Wang, Amir Barati Farimani

Fingerprint works on graph structure at the feature extraction stage, while GNNs directly handle molecule structure in both the feature extraction and model prediction stage.

Correcting Exposure Bias for Link Recommendation

1 code implementation13 Jun 2021 Shantanu Gupta, Hao Wang, Zachary C. Lipton, Yuyang Wang

Link prediction methods are frequently applied in recommender systems, e. g., to suggest citations for academic papers or friends in social networks.

Link Prediction Recommendation Systems

Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs

1 code implementation15 Mar 2024 S. Chandra Mouli, Danielle C. Maddix, Shima Alizadeh, Gaurav Gupta, Andrew Stuart, Michael W. Mahoney, Yuyang Wang

Existing work in scientific machine learning (SciML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical partial differential equation (PDE) solvers.

Uncertainty Quantification

Backpropagation through Back Substitution with a Backslash

1 code implementation23 Feb 2023 Alan Edelman, Ekin Akyurek, Yuyang Wang

This paper has three contributions: (i) it is of intellectual value to replace traditional treatments of automatic differentiation with a (left acting) operator theoretic, graph-based approach; (ii) operators can be readily placed in matrices in software in programming languages such as Julia as an implementation option; (iii) we introduce a novel notation, ``transpose dot'' operator ``$\{\}^{T_\bullet}$'' that allows for the reversal of operators.

Neural Network Predicts Ion Concentration Profiles under Nanoconfinement

1 code implementation10 Apr 2023 Zhonglin Cao, Yuyang Wang, Cooper Lorsung, Amir Barati Farimani

Overall, our deep learning model is a fast, flexible, and accurate surrogate model to predict ion concentration profiles in nanoconfinement.

Gini-regularized Optimal Transport with an Application to Spatio-Temporal Forecasting

no code implementations7 Dec 2017 Lucas Roberts, Leo Razoumov, Lin Su, Yuyang Wang

Moreover, we show that the Gini regularized OT problem converges to the classical OT problem, when the Gini regularized problem is considered as a function of {\lambda}, the regularization parame-ter.

Open-Ended Question Answering Spatio-Temporal Forecasting

Deep Factors with Gaussian Processes for Forecasting

no code implementations30 Nov 2018 Danielle C. Maddix, Yuyang Wang, Alex Smola

A large collection of time series poses significant challenges for classical and neural forecasting approaches.

Gaussian Processes Time Series +1

Deep Factors for Forecasting

no code implementations28 May 2019 Yuyang Wang, Alex Smola, Danielle C. Maddix, Jan Gasthaus, Dean Foster, Tim Januschowski

We provide both theoretical and empirical evidence for the soundness of our approach through a necessary and sufficient decomposition of exchangeable time series into a global and a local part.

Time Series Time Series Analysis

Site-specific online compressive beam codebook learning in mmWave vehicular communication

no code implementations11 May 2020 Yuyang Wang, Nitin Jonathan Myers, Nuria González-Prelcic, Robert W. Heath Jr

Furthermore, based on the CS channel measurements, we develop techniques to update and learn such channel AoD statistics at the BS.

Compressive Sensing

Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization

no code implementations12 Jan 2021 Yuyang Wang, Kenji Shimada, Amir Barati Farimani

Our model can (1) encode the existing airfoil into a latent vector and reconstruct the airfoil from that, (2) generate novel airfoils by randomly sampling the latent vectors and mapping the vectors to the airfoil coordinate domain, and (3) synthesize airfoils with desired aerodynamic properties by optimizing learned features via a genetic algorithm.

Generative Adversarial Network

Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination

no code implementations19 Jan 2021 Yuyang Wang, Zhonglin Cao, Amir Barati Farimani

Structure and geometry optimization of nanopores on such materials is beneficial for their performances in real-world engineering applications, like water desalination.

reinforcement-learning Reinforcement Learning (RL)

Variance Reduced Training with Stratified Sampling for Forecasting Models

no code implementations2 Mar 2021 Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean Foster

In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset.

Time Series Time Series Forecasting

Zero-Shot Recommender Systems

no code implementations18 May 2021 Hao Ding, Yifei Ma, Anoop Deoras, Yuyang Wang, Hao Wang

This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS.

Recommendation Systems Zero-Shot Learning

Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting

no code implementations12 Nov 2021 Youngsuk Park, Danielle Maddix, François-Xavier Aubet, Kelvin Kan, Jan Gasthaus, Yuyang Wang

Quantile regression is an effective technique to quantify uncertainty, fit challenging underlying distributions, and often provide full probabilistic predictions through joint learnings over multiple quantile levels.

Time Series Time Series Forecasting

Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR

no code implementations22 Nov 2021 Dheeraj Baby, Hilaf Hasson, Yuyang Wang

When the loss functions are strongly convex or exp-concave, we demonstrate that Strongly Adaptive (SA) algorithms can be viewed as a principled way of controlling dynamic regret in terms of path variation $V_T$ of the comparator sequence.

Open-Ended Question Answering regression

GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics

no code implementations18 Dec 2021 Ke Alexander Wang, Danielle Maddix, Yuyang Wang

We consider the problem of probabilistic forecasting over categories with graph structure, where the dynamics at a vertex depends on its local connectivity structure.

Inductive Bias

Graph Neural Networks for Molecules

no code implementations12 Sep 2022 Yuyang Wang, Zijie Li, Amir Barati Farimani

Graph neural networks (GNNs), which are capable of learning representations from graphical data, are naturally suitable for modeling molecular systems.

Molecular Property Prediction Property Prediction +1

Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function

no code implementations26 Oct 2022 Qing Wang, Hang Chen, Ya Jiang, Zhe Wang, Yuyang Wang, Jun Du, Chin-Hui Lee

In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function.

Criteria for Classifying Forecasting Methods

no code implementations7 Dec 2022 Tim Januschowski, Jan Gasthaus, Yuyang Wang, David Salinas, Valentin Flunkert, Michael Bohlke-Schneider, Laurent Callot

Classifying forecasting methods as being either of a "machine learning" or "statistical" nature has become commonplace in parts of the forecasting literature and community, as exemplified by the M4 competition and the conclusion drawn by the organizers.

Testing Causality for High Dimensional Data

no code implementations14 Mar 2023 Arun Jambulapati, Hilaf Hasson, Youngsuk Park, Yuyang Wang

Determining causal relationship between high dimensional observations are among the most important tasks in scientific discoveries.

Vocal Bursts Intensity Prediction

Dataset for predicting cybersickness from a virtual navigation task

no code implementations7 Feb 2023 Yuyang Wang, Ruichen Li, Jean-Rémy Chardonnet, Pan Hui

This work presents a dataset collected to predict cybersickness in virtual reality environments.

Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting

no code implementations25 May 2023 Hilaf Hasson, Danielle C. Maddix, Yuyang Wang, Gaurav Gupta, Youngsuk Park

Ensembling is among the most popular tools in machine learning (ML) due to its effectiveness in minimizing variance and thus improving generalization.

Time Series Time Series Forecasting

Manifold Diffusion Fields

no code implementations24 May 2023 Ahmed A. Elhag, Yuyang Wang, Joshua M. Susskind, Miguel Angel Bautista

Our approach allows to sample continuous functions on manifolds and is invariant with respect to rigid and isometric transformations of the manifold.

Efficient Task Offloading Algorithm for Digital Twin in Edge/Cloud Computing Environment

no code implementations12 Jul 2023 Ziru Zhang, Xuling Zhang, Guangzhi Zhu, Yuyang Wang, Pan Hui

In the era of Internet of Things (IoT), Digital Twin (DT) is envisioned to empower various areas as a bridge between physical objects and the digital world.

Cloud Computing Decision Making +1

Generating Molecular Conformer Fields

no code implementations27 Nov 2023 Yuyang Wang, Ahmed A. Elhag, Navdeep Jaitly, Joshua M. Susskind, Miguel Angel Bautista

In this paper we tackle the problem of generating conformers of a molecule in 3D space given its molecular graph.

Harnessing Machine Learning for Discerning AI-Generated Synthetic Images

no code implementations14 Jan 2024 Yuyang Wang, Yizhi Hao, Amando Xu Cong

Our application study contributes by applying and optimizing these advanced models for synthetic image detection, conducting a comparative analysis using various metrics, and demonstrating their superior capability in identifying AI-generated images over traditional machine learning techniques.

Synthetic Image Detection Transfer Learning

Rock Classification Based on Residual Networks

no code implementations19 Feb 2024 Sining Zhoubian, Yuyang Wang, Zhihuan Jiang

This boosts the model's performance, achieving an accuracy of 73. 7% on the test dataset.

Classification Data Augmentation

Explainable AI for Embedded Systems Design: A Case Study of Static Redundant NVM Memory Write Prediction

no code implementations7 Mar 2024 Abdoulaye Gamatié, Yuyang Wang

To achieve this, we propose a methodology consisting of: 1) the development of relevant ML models for explaining silent store prediction, and 2) the application of XAI to explain these models.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Cannot find the paper you are looking for? You can Submit a new open access paper.