12 citations · 41 across the 31 of their papers we have counts for
31 papers
Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment
Liang Wang, Junpeng Wang, Chin-chia Michael Yeh +6
Large Language Models (LLMs) are increasingly used as evaluators of reasoning quality, yet their reliability and bias in payments-risk settings remain poorly understood. We introdu…
TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding
Chin-Chia Michael Yeh, Uday Singh Saini, Xin Dai +12
Payment networks form the backbone of modern commerce, generating high volumes of transaction records from daily activities. Properly modeling this data can enable applications suc…
TransactionGPT
Yingtong Dou, Zhimeng Jiang, Tianyi Zhang +26
We present TransactionGPT (TGPT), a foundation model for consumer transaction data within one of the world's largest payment networks. TGPT is designed to understand and generate t…
UltraSTF: Ultra-Compact Model for Large-Scale Spatio-Temporal Forecasting
Chin-Chia Michael Yeh, Xiran Fan, Zhimeng Jiang +9
Spatio-temporal data, prevalent in real-world applications such as traffic monitoring, financial transactions, and ride-share demands, represents a specialized case of multivariate…
Preserving Individuality while Following the Crowd: Understanding the Role of User Taste and Crowd Wisdom in Online Product Rating Prediction
Liang Wang, Shubham Jain, Yingtong Dou +9
Numerous algorithms have been developed for online product rating prediction, but the specific influence of user and product information in determining the final prediction score r…
Matrix Profile for Anomaly Detection on Multidimensional Time Series
Chin-Chia Michael Yeh, Audrey Der, Uday Singh Saini +11
The Matrix Profile (MP), a versatile tool for time series data mining, has been shown effective in time series anomaly detection (TSAD). This paper delves into the problem of anoma…
A Systematic Evaluation of Generated Time Series and Their Effects in Self-Supervised Pretraining
Audrey Der, Chin-Chia Michael Yeh, Xin Dai +9
Self-supervised Pretrained Models (PTMs) have demonstrated remarkable performance in computer vision and natural language processing tasks. These successes have prompted researcher…
Compressing and Interpreting Word Embeddings with Latent Space Regularization and Interactive Semantics Probing
Haoyu Li, Junpeng Wang, Yan Zheng +3
Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, e.g.,…
Has Your Pretrained Model Improved? A Multi-head Posterior Based Approach
Prince Aboagye, Yan Zheng, Junpeng Wang +8
The emergence of pre-trained models has significantly impacted Natural Language Processing (NLP) and Computer Vision to relational datasets. Traditionally, these models are assesse…
RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
Chin-Chia Michael Yeh, Yujie Fan, Xin Dai +9
Spatial-temporal forecasting systems play a crucial role in addressing numerous real-world challenges. In this paper, we investigate the potential of addressing spatial-temporal fo…
PUPAE: Intuitive and Actionable Explanations for Time Series Anomalies
Audrey Der, Chin-Chia Michael Yeh, Yan Zheng +5
In recent years there has been significant progress in time series anomaly detection. However, after detecting an (perhaps tentative) anomaly, can we explain it? Such explanations…
Sketching Multidimensional Time Series for Fast Discord Mining
Chin-Chia Michael Yeh, Yan Zheng, Menghai Pan +7
Time series discords are a useful primitive for time series anomaly detection, and the matrix profile is capable of capturing discord effectively. There exist many research efforts…
Time Series Synthesis Using the Matrix Profile for Anonymization
Audrey Der, Chin-Chia Michael Yeh, Yan Zheng +6
Publishing and sharing data is crucial for the data mining community, allowing collaboration and driving open innovation. However, many researchers cannot release their data due to…
Ego-Network Transformer for Subsequence Classification in Time Series Data
Chin-Chia Michael Yeh, Huiyuan Chen, Yujie Fan +8
Time series classification is a widely studied problem in the field of time series data mining. Previous research has predominantly focused on scenarios where relevant or foregroun…
Temporal Treasure Hunt: Content-based Time Series Retrieval System for Discovering Insights
Chin-Chia Michael Yeh, Huiyuan Chen, Xin Dai +8
Time series data is ubiquitous across various domains such as finance, healthcare, and manufacturing, but their properties can vary significantly depending on the domain they origi…
Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning
Yiran Li, Junpeng Wang, Prince Aboagye +5
Recent advancements in pre-trained large-scale language-image models have ushered in a new era of visual comprehension, offering a significant leap forward. These breakthroughs hav…
FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Data
Dongyu Zhang, Liang Wang, Xin Dai +7
Sequential tabular data is one of the most commonly used data types in real-world applications. Different from conventional tabular data, where rows in a table are independent, seq…
Multitask Learning for Time Series Data with 2D Convolution
Chin-Chia Michael Yeh, Xin Dai, Yan Zheng +7
Multitask learning (MTL) aims to develop a unified model that can handle a set of closely related tasks simultaneously. By optimizing the model across multiple tasks, MTL generally…
An Efficient Content-based Time Series Retrieval System
Chin-Chia Michael Yeh, Huiyuan Chen, Xin Dai +9
A Content-based Time Series Retrieval (CTSR) system is an information retrieval system for users to interact with time series emerged from multiple domains, such as finance, health…
Toward a Foundation Model for Time Series Data
Chin-Chia Michael Yeh, Xin Dai, Huiyuan Chen +8
A foundation model is a machine learning model trained on a large and diverse set of data, typically using self-supervised learning-based pre-training techniques, that can be adapt…
EmbeddingTree: Hierarchical Exploration of Entity Features in Embedding
Yan Zheng, Junpeng Wang, Chin-Chia Michael Yeh +4
Embedding learning transforms discrete data entities into continuous numerical representations, encoding features/properties of the entities. Despite the outstanding performance re…
PDT: Pretrained Dual Transformers for Time-aware Bipartite Graphs
Xin Dai, Yujie Fan, Zhongfang Zhuang +7
Pre-training on large models is prevalent and emerging with the ever-growing user-generated content in many machine learning application categories. It has been recognized that lea…
How Does Attention Work in Vision Transformers? A Visual Analytics Attempt
Yiran Li, Junpeng Wang, Xin Dai +5
Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a…
Matrix Profile XXVII: A Novel Distance Measure for Comparing Long Time Series
Audrey Der, Chin-Chia Michael Yeh, Renjie Wu +6
The most useful data mining primitives are distance measures. With an effective distance measure, it is possible to perform classification, clustering, anomaly detection, segmentat…