no code implementations • 26 May 2024 • Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, QIngwei Lin, Alois Knoll, Ming Jin
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints.
no code implementations • 26 May 2024 • Vanshaj Khattar, Yuhao Ding, Bilgehan Sel, Javad Lavaei, Ming Jin
Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience.
no code implementations • 21 May 2024 • Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin
Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering.
no code implementations • 18 May 2024 • Ming Jin
Operating safely and reliably despite continual distribution shifts is vital for high-stakes machine learning applications.
2 code implementations • 2 May 2024 • Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, QIngwei Lin, Ming Jin, Alois Knoll
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications.
1 code implementation • 29 Apr 2024 • Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Jiang Bian, Shirui Pan, Qingsong Wen
Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks.
no code implementations • 21 Mar 2024 • Yuxuan Liang, Haomin Wen, Yuqi Nie, Yushan Jiang, Ming Jin, Dongjin Song, Shirui Pan, Qingsong Wen
Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications.
no code implementations • 15 Mar 2024 • Junteng Yao, Tuo Wu, Ming Jin, Cunhua Pan, Quanzhong Li, Jinhong Yuan
This paper investigates covert data transmission within a multiple-input multiple-output (MIMO) over-the-air computation (AirComp) network, where sensors transmit data to the access point (AP) while guaranteeing covertness to the warden (Willie).
no code implementations • 13 Mar 2024 • Shangding Gu, Alois Knoll, Ming Jin
The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries tied to the self-instruct paradigm.
no code implementations • 1 Mar 2024 • Junteng Yao, Liaoshi Zhou, Tuo Wu, Ming Jin, Cunhua Pan, Maged Elkashlan, Kai-Kit Wong
This paper addresses the fairness issue within fluid antenna system (FAS)-assisted non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) systems, where a single fixed-antenna base station (BS) transmits superposition-coded signals to two users, each with a single fluid antenna.
no code implementations • 18 Feb 2024 • Jiaxi Hu, Yuehong Hu, Wei Chen, Ming Jin, Shirui Pan, Qingsong Wen, Yuxuan Liang
In long-term time series forecasting (LTSF) tasks, an increasing number of models have acknowledged that discrete time series originate from continuous dynamic systems and have attempted to model their dynamical structures.
no code implementations • 14 Feb 2024 • Myeongseob Ko, Feiyang Kang, Weiyan Shi, Ming Jin, Zhou Yu, Ruoxi Jia
Inspired by this, we introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point.
no code implementations • 5 Feb 2024 • Ming Jin, Yifan Zhang, Wei Chen, Kexin Zhang, Yuxuan Liang, Bin Yang, Jindong Wang, Shirui Pan, Qingsong Wen
Time series analysis is essential for comprehending the complexities inherent in various real-world systems and applications.
no code implementations • 11 Jan 2024 • Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Haishuai Wang, Khoa T. Phan, Yi-Ping Phoebe Chen, Shirui Pan, Wei Xiang
However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values.
no code implementations • 10 Jan 2024 • Shubao Zhao, Ming Jin, Zhaoxiang Hou, Chengyi Yang, Zengxiang Li, Qingsong Wen, Yi Wang
Time series forecasting is crucial and challenging in the real world.
no code implementations • 28 Dec 2023 • Padmaksha Roy, Tyler Cody, Himanshu Singhal, Kevin Choi, Ming Jin
Domain generalization focuses on leveraging knowledge from multiple related domains with ample training data and labels to enhance inference on unseen in-distribution (IN) and out-of-distribution (OOD) domains.
5 code implementations • 16 Oct 2023 • Ming Jin, Qingsong Wen, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang, Yi Wang, Haifeng Chen, XiaoLi Li, Shirui Pan, Vincent S. Tseng, Yu Zheng, Lei Chen, Hui Xiong
In this survey, we offer a comprehensive and up-to-date review of large models tailored (or adapted) for time series and spatio-temporal data, spanning four key facets: data types, model categories, model scopes, and application areas/tasks.
no code implementations • 11 Oct 2023 • Junteng Yao, Tuo Wu, Xiazhi Lai, Ming Jin, Cunhua Pan, Maged Elkashlan, Kai-Kit Wong
Our objective is to maximize the average monitoring rate, whose expression involves the integral of the first-order Marcum $Q$ function.
2 code implementations • 3 Oct 2023 • Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y. Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, Qingsong Wen
We begin by reprogramming the input time series with text prototypes before feeding it into the frozen LLM to align the two modalities.
1 code implementation • ICCV 2023 • Myeongseob Ko, Ming Jin, Chenguang Wang, Ruoxi Jia
Furthermore, our enhanced attacks outperform the baseline across multiple models and datasets, with the weakly supervised attack demonstrating an average-case performance improvement of $17\%$ and being at least $7$X more effective at low false-positive rates.
no code implementations • 1 Sep 2023 • Yiwen Mao, Dawei Gao, Qinghua Guo, Ming Jin
This work deals with directional of arrival (DOA) estimation with a large antenna array.
no code implementations • 20 Aug 2023 • Bilgehan Sel, Ahmad Al-Tawaha, Vanshaj Khattar, Ruoxi Jia, Ming Jin
Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to an external modus operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models' (LLMs) reasoning capacities.
no code implementations • 20 Aug 2023 • Ming Jin, Bilgehan Sel, Fnu Hardeep, Wotao Yin
This paper outlines a natural conversational approach to solving personalized energy-related problems using large language models (LLMs).
1 code implementation • 10 Aug 2023 • Siqiao Xue, Fan Zhou, Yi Xu, Ming Jin, Qingsong Wen, Hongyan Hao, Qingyang Dai, Caigao Jiang, Hongyu Zhao, Shuo Xie, Jianshan He, James Zhang, Hongyuan Mei
We present WeaverBird, an intelligent dialogue system designed specifically for the finance domain.
1 code implementation • 17 Jul 2023 • Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen, Wei Xiang
To overcome these limitations, we propose a novel method, correlation-aware spatial-temporal graph learning (termed CST-GL), for time series anomaly detection.
1 code implementation • 7 Jul 2023 • Ming Jin, Huan Yee Koh, Qingsong Wen, Daniele Zambon, Cesare Alippi, Geoffrey I. Webb, Irwin King, Shirui Pan
In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation.
1 code implementation • 16 Jun 2023 • Kexin Zhang, Qingsong Wen, Chaoli Zhang, Rongyao Cai, Ming Jin, Yong liu, James Zhang, Yuxuan Liang, Guansong Pang, Dongjin Song, Shirui Pan
To fill this gap, we review current state-of-the-art SSL methods for time series data in this article.
no code implementations • 21 May 2023 • Guangsi Shi, Daokun Zhang, Ming Jin, Shirui Pan, Philip S. Yu
To better comprehend the complex physical laws, this paper proposes a novel learning based simulation model- Graph Networks with Spatial-Temporal neural Ordinary Equations (GNSTODE)- that characterizes the varying spatial and temporal dependencies in particle systems using a united end-to-end framework.
no code implementations • 11 May 2023 • Ming Jin, Guangsi Shi, Yuan-Fang Li, Qingsong Wen, Bo Xiong, Tian Zhou, Shirui Pan
In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs.
1 code implementation • 28 Apr 2023 • Hoang Anh Just, Feiyang Kang, Jiachen T. Wang, Yi Zeng, Myeongseob Ko, Ming Jin, Ruoxi Jia
(1) We develop a proxy for the validation performance associated with a training set based on a non-conventional class-wise Wasserstein distance between training and validation sets.
no code implementations • 24 Apr 2023 • Bo Xiong, Mojtaba Nayyeri, Ming Jin, Yunjie He, Michael Cochez, Shirui Pan, Steffen Staab
Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions.
Hierarchical Multi-label Classification Knowledge Graph Completion +1
1 code implementation • 10 Mar 2023 • Mohammad S. Ramadan, Ahmad Al-Tawaha, Mohamed Shouman, Ahmed Atallah, Ming Jin
This paper presents a Monte Carlo-based sampling approach for the state space and an interpolation procedure for the resulting value function, dependent on the process noise density, in a "self-approximating" fashion, eliminating the need for ordering or set-membership tests.
no code implementations • 4 Dec 2022 • Vanshaj Khattar, Ming Jin
Modern power systems will have to face difficult challenges in the years to come: frequent blackouts in urban areas caused by high power demand peaks, grid instability exacerbated by intermittent renewable generation, and global climate change amplified by rising carbon emissions.
no code implementations • 2 Dec 2022 • Ming Jin, Vanshaj Khattar, Harshal Kaushik, Bilgehan Sel, Ruoxi Jia
We study the expressibility and learnability of convex optimization solution functions and their multi-layer architectural extension.
no code implementations • 19 Nov 2022 • Yuhao Ding, Ming Jin, Javad Lavaei
We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs).
no code implementations • 9 Nov 2022 • Dawei Gao, Qinghua Guo, Ming Jin, Guisheng Liao, Yonina C. Eldar
Choosing the values of hyper-parameters in sparse Bayesian learning (SBL) can significantly impact performance.
no code implementations • 1 Nov 2022 • Enwei Zhu, Yiyang Liu, Ming Jin, Jinpeng Li
However, existing nested NER models heavily rely on training data annotated with nested entities, while labeling such data is costly.
no code implementations • 25 Oct 2022 • Zhaoji Zhang, Qinghua Guo, Ying Li, Ming Jin, Chongwen Huang
Furthermore, in conjunction with the AMP algorithm, a variational Bayesian inference based clustering (VBIC) algorithm is developed to solve this clustering problem.
1 code implementation • 12 Oct 2022 • Yi Zeng, Minzhou Pan, Himanshu Jahagirdar, Ming Jin, Lingjuan Lyu, Ruoxi Jia
Most poisoning defenses presume access to a set of clean data (or base set).
no code implementations • 23 Feb 2022 • Zain ul Abdeen, He Yin, Vassilis Kekatos, Ming Jin
In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors.
1 code implementation • 17 Feb 2022 • Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen, Bin Yang, Shirui Pan
Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction.
no code implementations • 11 Feb 2022 • Yu Zheng, Ming Jin, Yixin Liu, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen
Anomaly detection from graph data is an important data mining task in many applications such as social networks, finance, and e-commerce.
no code implementations • 20 Nov 2021 • Yizhen Zheng, Ming Jin, Shirui Pan, Yuan-Fang Li, Hao Peng, Ming Li, Zhao Li
To overcome the aforementioned problems, we introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming, namely G-Zoom, to learn node representations by leveraging the proposed adjusted zooming scheme.
3 code implementations • ICLR 2022 • Yi Zeng, Si Chen, Won Park, Z. Morley Mao, Ming Jin, Ruoxi Jia
Particularly, its performance is more robust to the variation on triggers, attack settings, poison ratio, and clean data size.
no code implementations • 29 Sep 2021 • Tianhao Wang, Yi Zeng, Ming Jin, Ruoxi Jia
In this paper, we focus on the problem of identifying bad training data when the underlying cause is unknown in advance.
no code implementations • 29 Sep 2021 • Ming Jin, Yuan-Fang Li, Yu Zheng, Bin Yang, Shirui Pan
Spatiotemporal representation learning on multivariate time series has received tremendous attention in forecasting traffic and energy data.
1 code implementation • 8 Sep 2021 • Fangda Gu, He Yin, Laurent El Ghaoui, Murat Arcak, Peter Seiler, Ming Jin
Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity.
1 code implementation • 23 Aug 2021 • Yu Zheng, Ming Jin, Yixin Liu, Lianhua Chi, Khoa T. Phan, Yi-Ping Phoebe Chen
While the generative attribute regression module allows us to capture the anomalies in the attribute space, the multi-view contrastive learning module can exploit richer structure information from multiple subgraphs, thus abling to capture the anomalies in the structure space, mixing of structure, and attribute information.
1 code implementation • 16 Jul 2021 • Hao Chen, Ming Jin, Zhunan Li, Cunhang Fan, Jinpeng Li, Huiguang He
Although several studies have adopted domain adaptation (DA) approaches to tackle this problem, most of them treat multiple EEG data from different subjects and sessions together as a single source domain for transfer, which either fails to satisfy the assumption of domain adaptation that the source has a certain marginal distribution, or increases the difficulty of adaptation.
no code implementations • 10 Jun 2021 • Tianhao Wang, Yi Zeng, Ming Jin, Ruoxi Jia
High-quality data is critical to train performant Machine Learning (ML) models, highlighting the importance of Data Quality Management (DQM).
1 code implementation • 12 May 2021 • Ming Jin, Yizhen Zheng, Yuan-Fang Li, Chen Gong, Chuan Zhou, Shirui Pan
To overcome this problem, inspired by the recent success of graph contrastive learning and Siamese networks in visual representation learning, we propose a novel self-supervised approach in this paper to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning.
no code implementations • 2 May 2021 • Sarthak Gupta, Vassilis Kekatos, Ming Jin
The trained DNNs can be driven by partial, noisy, or proxy descriptors of the current grid conditions.
3 code implementations • 27 Feb 2021 • Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou, Yu Zheng, Feng Xia, Philip S. Yu
Deep learning on graphs has attracted significant interests recently.
no code implementations • 25 Jan 2021 • Man Luo, Qinghua Guo, Ming Jin, Yonina C. Eldar, Defeng, Huang, Xiangming Meng
Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm.
1 code implementation • 16 Dec 2020 • He Yin, Peter Seiler, Ming Jin, Murat Arcak
A method is presented to learn neural network (NN) controllers with stability and safety guarantees through imitation learning (IL).
no code implementations • 25 Sep 2019 • Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi
By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.
1 code implementation • 24 May 2019 • Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi
By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.
no code implementations • 26 Oct 2018 • Ming Jin, Javad Lavaei
We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems.
no code implementations • 26 Dec 2015 • Ming Jin, Andreas Damianou, Pieter Abbeel, Costas Spanos
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations.
no code implementations • 22 Jun 2014 • Ming Jin, Han Zou, Kevin Weekly, Ruoxi Jia, Alexandre M. Bayen, Costas J. Spanos
We present results from a set of experiments in this pilot study to investigate the causal influence of user activity on various environmental parameters monitored by occupant carried multi-purpose sensors.