Search Results for author: Jianmin Wang

Found 53 papers, 31 papers with code

CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding

no code implementations3 May 2024 Kaiyuan Chen, Xingzhuo Guo, Yu Zhang, Jianmin Wang, Mingsheng Long

The precision weighting mechanism posits that the brain allocates more attention to signals with lower precision, contributing to the cognitive ability of human brains.

Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model

1 code implementation20 Mar 2024 Peng Zhou, Jianmin Wang, Chunyan Li, Zixu Wang, Yiping Liu, Siqi Sun, Jianxin Lin, Longyue Wang, Xiangxiang Zeng

While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge.

Drug Discovery Knowledge Distillation +2

depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers

1 code implementation14 Mar 2024 Kaichao You, Runsheng Bai, Meng Cao, Jianmin Wang, Ion Stoica, Mingsheng Long

PyTorch \texttt{2. x} introduces a compiler designed to accelerate deep learning programs.

TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables

no code implementations29 Feb 2024 Yuxuan Wang, Haixu Wu, Jiaxiang Dong, Yong liu, Yunzhong Qiu, Haoran Zhang, Jianmin Wang, Mingsheng Long

Experimentally, TimeXer significantly improves time series forecasting with exogenous variables and achieves consistent state-of-the-art performance in twelve real-world forecasting benchmarks.

Time Series Time Series Forecasting

TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling

no code implementations4 Feb 2024 Jiaxiang Dong, Haixu Wu, Yuxuan Wang, Yunzhong Qiu, Li Zhang, Jianmin Wang, Mingsheng Long

To emphasize temporal correlation modeling, this paper proposes TimeSiam as a simple but effective self-supervised pre-training framework for Time series based on Siamese networks.

Contrastive Learning Data Augmentation +1

Transolver: A Fast Transformer Solver for PDEs on General Geometries

no code implementations4 Feb 2024 Haixu Wu, Huakun Luo, Haowen Wang, Jianmin Wang, Mingsheng Long

Transformers have empowered many milestones across various fields and have recently been applied to solve partial differential equations (PDEs).

Timer: Transformers for Time Series Analysis at Scale

1 code implementation4 Feb 2024 Yong liu, Haoran Zhang, Chenyu Li, Xiangdong Huang, Jianmin Wang, Mingsheng Long

Continuous progresses have been achieved as the emergence of large language models, exhibiting unprecedented ability in few-shot generalization, scalability, and task generality, which is however absent in time series models.

Anomaly Detection Imputation +2

AutoTimes: Autoregressive Time Series Forecasters via Large Language Models

1 code implementation4 Feb 2024 Yong liu, Guo Qin, Xiangdong Huang, Jianmin Wang, Mingsheng Long

Foundation models of time series have not been fully developed due to the limited availability of large-scale time series and the underexploration of scalable pre-training.

In-Context Learning Language Modelling +1

EuLagNet: Eulerian Fluid Prediction with Lagrangian Dynamics

no code implementations4 Feb 2024 Qilong Ma, Haixu Wu, Lanxiang Xing, Jianmin Wang, Mingsheng Long

Accurately predicting the future fluid is important to extensive areas, such as meteorology, oceanology and aerodynamics.

Future prediction

HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction

no code implementations16 Oct 2023 Lanxiang Xing, Haixu Wu, Yuezhou Ma, Jianmin Wang, Mingsheng Long

Compared with previous velocity estimating methods, HelmFluid is faithfully derived from Helmholtz theorem and ravels out complex fluid dynamics with physically interpretable evidence.

Future prediction

HarmonyDream: Task Harmonization Inside World Models

no code implementations30 Sep 2023 Haoyu Ma, Jialong Wu, Ningya Feng, Chenjun Xiao, Dong Li, Jianye Hao, Jianmin Wang, Mingsheng Long

Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically encompasses components for two tasks: observation modeling and reward modeling.

Atari Games 100k Model-based Reinforcement Learning +1

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

2 code implementations NeurIPS 2023 Yong liu, Chenyu Li, Jianmin Wang, Mingsheng Long

While previous models suffer from complicated series variations induced by changing temporal distribution, we tackle non-stationary time series with modern Koopman theory that fundamentally considers the underlying time-variant dynamics.

Time Series

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

1 code implementation NeurIPS 2023 Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang, Jianmin Wang, Mingsheng Long

By relating masked modeling to manifold learning, SimMTM proposes to recover masked time points by the weighted aggregation of multiple neighbors outside the manifold, which eases the reconstruction task by assembling ruined but complementary temporal variations from multiple masked series.

Representation Learning Time Series +1

CLIPood: Generalizing CLIP to Out-of-Distributions

1 code implementation2 Feb 2023 Yang Shu, Xingzhuo Guo, Jialong Wu, Ximei Wang, Jianmin Wang, Mingsheng Long

This paper aims at generalizing CLIP to out-of-distribution test data on downstream tasks.

Solving High-Dimensional PDEs with Latent Spectral Models

1 code implementation30 Jan 2023 Haixu Wu, Tengge Hu, Huakun Luo, Jianmin Wang, Mingsheng Long

A burgeoning paradigm is learning neural operators to approximate the input-output mappings of PDEs.

Vocal Bursts Intensity Prediction

TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

3 code implementations5 Oct 2022 Haixu Wu, Tengge Hu, Yong liu, Hang Zhou, Jianmin Wang, Mingsheng Long

TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block.

Action Recognition Anomaly Detection +4

Requirements Engineering for Machine Learning: A Review and Reflection

no code implementations3 Oct 2022 Zhongyi Pei, Lin Liu, Chen Wang, Jianmin Wang

Today, many industrial processes are undergoing digital transformation, which often requires the integration of well-understood domain models and state-of-the-art machine learning technology in business processes.

Decision Making

Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models

no code implementations8 Jun 2022 Yang Shu, Zhangjie Cao, Ziyang Zhang, Jianmin Wang, Mingsheng Long

The proposed framework can be trained end-to-end with the target task-specific loss, where it learns to explore better pathway configurations and exploit the knowledge in pre-trained models for each target datum.

Transfer Learning

Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting

2 code implementations28 May 2022 Yong liu, Haixu Wu, Jianmin Wang, Mingsheng Long

However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time.

Time Series Time Series Forecasting

MetaSets: Meta-Learning on Point Sets for Generalizable Representations

no code implementations CVPR 2021 Chao Huang, Zhangjie Cao, Yunbo Wang, Jianmin Wang, Mingsheng Long

It is a challenging problem due to the substantial geometry shift from simulated to real data, such that most existing 3D models underperform due to overfitting the complete geometries in the source domain.

Domain Generalization Meta-Learning

From Big to Small: Adaptive Learning to Partial-Set Domains

1 code implementation14 Mar 2022 Zhangjie Cao, Kaichao You, Ziyang Zhang, Jianmin Wang, Mingsheng Long

Still, the common requirement of identical class space shared across domains hinders applications of domain adaptation to partial-set domains.

Partial Domain Adaptation

Flowformer: Linearizing Transformers with Conservation Flows

1 code implementation13 Feb 2022 Haixu Wu, Jialong Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long

By respectively conserving the incoming flow of sinks for source competition and the outgoing flow of sources for sink allocation, Flow-Attention inherently generates informative attentions without using specific inductive biases.

Ranked #4 on D4RL on D4RL

D4RL Offline RL +2

Supported Policy Optimization for Offline Reinforcement Learning

3 code implementations13 Feb 2022 Jialong Wu, Haixu Wu, Zihan Qiu, Jianmin Wang, Mingsheng Long

Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy.

Offline RL reinforcement-learning +1

What Makes the Story Forward? Inferring Commonsense Explanations as Prompts for Future Event Generation

no code implementations18 Jan 2022 Li Lin, Yixin Cao, Lifu Huang, Shu'ang Li, Xuming Hu, Lijie Wen, Jianmin Wang

To alleviate the knowledge forgetting issue, we design two modules, Im and Gm, for each type of knowledge, which are combined via prompt tuning.

Information Retrieval Retrieval +1

Transferability in Deep Learning: A Survey

1 code implementation15 Jan 2022 Junguang Jiang, Yang Shu, Jianmin Wang, Mingsheng Long

The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when encountering and solving unseen tasks.

Domain Adaptation Transfer Learning

Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs

1 code implementation20 Oct 2021 Kaichao You, Yong liu, Ziyang Zhang, Jianmin Wang, Michael I. Jordan, Mingsheng Long

(2) The best ranked PTM can either be fine-tuned and deployed if we have no preference for the model's architecture or the target PTM can be tuned by the top $K$ ranked PTMs via a Bayesian procedure that we propose.

Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning

no code implementations14 Oct 2021 Yang Shu, Zhangjie Cao, Jinghan Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long

While pre-training and meta-training can create deep models powerful for few-shot generalization, we find that pre-training and meta-training focuses respectively on cross-domain transferability and cross-task transferability, which restricts their data efficiency in the entangled settings of domain shift and task shift.

Few-Shot Learning Transfer Learning

X-model: Improving Data Efficiency in Deep Learning with A Minimax Model

no code implementations ICLR 2022 Ximei Wang, Xinyang Chen, Jianmin Wang, Mingsheng Long

To take the power of both worlds, we propose a novel X-model by simultaneously encouraging the invariance to {data stochasticity} and {model stochasticity}.

Age Estimation Object Recognition +2

ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning

1 code implementation8 Oct 2021 Zhiyu Yao, Yunbo Wang, Haixu Wu, Jianmin Wang, Mingsheng Long

To this end, we propose ModeRNN, which introduces a novel method to learn structured hidden representations between recurrent states.

Inductive Bias

Decoupled Adaptation for Cross-Domain Object Detection

2 code implementations ICLR 2022 Junguang Jiang, Baixu Chen, Jianmin Wang, Mingsheng Long

Besides, previous methods focused on category adaptation but ignored another important part for object detection, i. e., the adaptation on bounding box regression.

Domain Adaptation Object +3

Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

3 code implementations ICLR 2022 Jiehui Xu, Haixu Wu, Jianmin Wang, Mingsheng Long

Unsupervised detection of anomaly points in time series is a challenging problem, which requires the model to derive a distinguishable criterion.

Anomaly Detection Time Series +1

The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations18 Sep 2021 Yanwei Fu, Feng Li, Paula boned Fustel, Lei Zhao, Lijie Jia, Haojie Zheng, Qiang Sun, Shisong Rong, Haicheng Tang, xiangyang xue, Li Yang, Hong Li, Jiao Xie Wenxuan Wang, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian, Mengwei Gu

The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0. 913 (95% CI, 0. 898-0. 927), with a sensitivity of 0. 695 (95% CI, 0. 643-0. 748), a specificity of 0. 904 (95% CI, 0. 891 -0. 919), an accuracy of 0. 875(0. 861-0. 889), and a F1 of 0. 611(0. 568-0. 655).

Binary Classification Specificity

Zoo-Tuning: Adaptive Transfer from a Zoo of Models

no code implementations29 Jun 2021 Yang Shu, Zhi Kou, Zhangjie Cao, Jianmin Wang, Mingsheng Long

We propose \emph{Zoo-Tuning} to address these challenges, which learns to adaptively transfer the parameters of pretrained models to the target task.

Facial Landmark Detection Image Classification +1

Transferable Query Selection for Active Domain Adaptation

no code implementations CVPR 2021 Bo Fu, Zhangjie Cao, Jianmin Wang, Mingsheng Long

Due to the domain shift, the query selection criteria of prior active learning methods may be ineffective to select the most informative target samples for annotation.

Active Learning Unsupervised Domain Adaptation

Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations12 Jun 2021 Yanwei Fu, Lei Zhao, Haojie Zheng, Qiang Sun, Li Yang, Hong Li, Jiao Xie, xiangyang xue, Feng Li, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian Mengwei Gu1

It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts.

Ethics

MetaSets:Meta-Learning on Point Sets for Generalizable Representations

no code implementations CVPR 2021 Chao Huang, Zhangjie Cao, Yunbo Wang, Jianmin Wang, Mingsheng Long

It is a challenging problem due to the substantial geometry shift from simulated to real data, such that most existing 3D models underperform due to overfitting the complete geometries in the source domain.

Domain Generalization

Open Domain Generalization with Domain-Augmented Meta-Learning

no code implementations CVPR 2021 Yang Shu, Zhangjie Cao, Chenyu Wang, Jianmin Wang, Mingsheng Long

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable.

Domain Generalization Meta-Learning

PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning

3 code implementations17 Mar 2021 Yunbo Wang, Haixu Wu, Jianjin Zhang, Zhifeng Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long

This paper models these structures by presenting PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment.

 Ranked #1 on Video Prediction on KTH (Cond metric)

Video Prediction Weather Forecasting

Regressive Domain Adaptation for Unsupervised Keypoint Detection

2 code implementations CVPR 2021 Junguang Jiang, Yifei Ji, Ximei Wang, Yufeng Liu, Jianmin Wang, Mingsheng Long

First, based on our observation that the probability density of the output space is sparse, we introduce a spatial probability distribution to describe this sparsity and then use it to guide the learning of the adversarial regressor.

Domain Adaptation Keypoint Detection

MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions

1 code implementation CVPR 2021 Haixu Wu, Zhiyu Yao, Jianmin Wang, Mingsheng Long

With high flexibility, this framework can adapt to a series of models for deterministic spatiotemporal prediction.

Video Prediction

Self-Tuning for Data-Efficient Deep Learning

2 code implementations25 Feb 2021 Ximei Wang, Jinghan Gao, Mingsheng Long, Jianmin Wang

Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets.

Transfer Learning

LogME: Practical Assessment of Pre-trained Models for Transfer Learning

1 code implementation22 Feb 2021 Kaichao You, Yong liu, Jianmin Wang, Mingsheng Long

In pursuit of a practical assessment method, we propose to estimate the maximum value of label evidence given features extracted by pre-trained models.

Model Selection regression +2

GAHNE: Graph-Aggregated Heterogeneous Network Embedding

no code implementations23 Dec 2020 Xiaohe Li, Lijie Wen, Chen Qian, Jianmin Wang

Heterogeneous network embedding aims to embed nodes into low-dimensional vectors which capture rich intrinsic information of heterogeneous networks.

Network Embedding

Learning to Adapt to Evolving Domains

1 code implementation NeurIPS 2020 Hong Liu, Mingsheng Long, Jianmin Wang, Yu Wang

(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.

Meta-Learning Transfer Learning +1

Co-Tuning for Transfer Learning

2 code implementations NeurIPS 2020 Kaichao You, Zhi Kou, Mingsheng Long, Jianmin Wang

Fine-tuning pre-trained deep neural networks (DNNs) to a target dataset, also known as transfer learning, is widely used in computer vision and NLP.

Image Classification Transfer Learning +1

Stochastic Normalization

2 code implementations NeurIPS 2020 Zhi Kou, Kaichao You, Mingsheng Long, Jianmin Wang

During training, two branches are stochastically selected to avoid over-depending on some sample statistics, resulting in a strong regularization effect, which we interpret as ``architecture regularization.''

Bi-tuning of Pre-trained Representations

no code implementations12 Nov 2020 Jincheng Zhong, Ximei Wang, Zhi Kou, Jianmin Wang, Mingsheng Long

It is common within the deep learning community to first pre-train a deep neural network from a large-scale dataset and then fine-tune the pre-trained model to a specific downstream task.

Contrastive Learning Unsupervised Pre-training

VideoDG: Generalizing Temporal Relations in Videos to Novel Domains

1 code implementation8 Dec 2019 Zhiyu Yao, Yunbo Wang, Jianmin Wang, Philip S. Yu, Mingsheng Long

This paper introduces video domain generalization where most video classification networks degenerate due to the lack of exposure to the target domains of divergent distributions.

Action Recognition Data Augmentation +5

Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation

2 code implementations International Conference on Machine Learning 2019 Xinyang Chen, Sinan Wang, Mingsheng Long, Jianmin Wang

In this paper, a series of experiments based on spectral analysis of the feature representations have been conducted, revealing an unexpected deterioration of the discriminability while learning transferable features adversarially.

Domain Adaptation Transfer Learning

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