Search Results for author:
Found 45 papers, 5 papers with code
Towards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformers
However, its practical application in large-scale settings is limited by quadratic time and space complexity ($O(N^2)$) with respect to the number of entities $N$.
A Compact Model for Large-Scale Time Series Forecasting
SparseTSF, a recently introduced competitive univariate forecasting model, harnesses periodicity to achieve compactness by concentrating on cross-period dynamics, thereby extending the Pareto frontier with respect to model size and predictive performance.
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
Large Language Models (LLMs) are becoming essential tools for various natural language processing tasks but often suffer from generating outdated or incorrect information.
Matrix Profile for Anomaly Detection on Multidimensional Time Series
This paper delves into the problem of anomaly detection in multidimensional time series, a common occurrence in real-world applications.
Preserving Individuality while Following the Crowd: Understanding the Role of User Taste and Crowd Wisdom in Online Product Rating Prediction
Our findings underscore the significance of individual user tastes in the context of online product rating prediction and the robustness of our approach across different model architectures.
A Systematic Evaluation of Generated Time Series and Their Effects in Self-Supervised Pretraining
Self-supervised Pretrained Models (PTMs) have demonstrated remarkable performance in computer vision and natural language processing tasks.
Masked Graph Transformer for Large-Scale Recommendation
Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes.
RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
Spatial-temporal forecasting systems play a crucial role in addressing numerous real-world challenges.
Ranked #6 on
Traffic Prediction
on LargeST
PUPAE: Intuitive and Actionable Explanations for Time Series Anomalies
In this work we introduce a domain agnostic counterfactual explanation technique to produce explanations for time series anomalies.
Sketching Multidimensional Time Series for Fast Discord Mining
In this work, we propose a sketch for discord mining among multi-dimensional time series.
Temporal Treasure Hunt: Content-based Time Series Retrieval System for Discovering Insights
To facilitate this investigation, we introduce a CTSR benchmark dataset that comprises time series data from a variety of domains, such as motion, power demand, and traffic.
Time Series Synthesis Using the Matrix Profile for Anonymization
As a result, unmodified data mining tools can obtain near-identical performance on the synthesized time series as on the original time series.
Ego-Network Transformer for Subsequence Classification in Time Series Data
The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph.
FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Data
FATA-Trans is field- and time-aware for sequential tabular data.
Toward a Foundation Model for Time Series Data
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 adapted to various downstream tasks.
An Efficient Content-based Time Series Retrieval System
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, healthcare, and manufacturing.
Multitask Learning for Time Series Data with 2D Convolution
In this paper, we investigate the application of MTL to the time series classification (TSC) problem.
Revealing the Power of Masked Autoencoders in Traffic Forecasting
Our results on traffic benchmarks show that STMAE can largely enhance the forecasting capabilities of various spatial-temporal models.
Hessian-aware Quantized Node Embeddings for Recommendation
To address the gradient mismatch problem in STE, we further consider the quantized errors and its second-order derivatives for better stability.
Adversarial Collaborative Filtering for Free
In this paper, we present Sharpness-aware Collaborative Filtering (SharpCF), a simple yet effective method that conducts adversarial training without extra computational cost over the base optimizer.
Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
Despite their success, Transformer-based models often require the optimization of a large number of parameters, making them difficult to train from sparse data in sequential recommendation.
EmbeddingTree: Hierarchical Exploration of Entity Features in Embedding
The tool helps users discover nuance features of data entities, perform feature denoising/injecting in embedding training, and generate embeddings for unseen entities.
Sharpness-Aware Graph Collaborative Filtering
Graph Neural Networks (GNNs) have achieved impressive performance in collaborative filtering.
PDT: Pretrained Dual Transformers for Time-aware Bipartite Graphs
Pre-training on large models is prevalent and emerging with the ever-growing user-generated content in many machine learning application categories.
How Does Attention Work in Vision Transformers? A Visual Analytics Attempt
Multi-head self-attentions are then applied to the sequence to learn the attention between patches.
Matrix Profile XXVII: A Novel Distance Measure for Comparing Long Time Series
PRCIS is a distance measure for long time series, which exploits recent progress in our ability to summarize time series with dictionaries.
Denoising Self-attentive Sequential Recommendation
Transformer-based sequential recommenders are very powerful for capturing both short-term and long-term sequential item dependencies.
TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems
We found that our TinyKG with INT2 quantization aggressively reduces the memory footprint of activation maps with $7 \times$, only with $2\%$ loss in accuracy, allowing us to deploy KGNNs on memory-constrained devices.
Dynamic Graph Node Classification via Time Augmentation
Node classification on dynamic graphs is challenging for two reasons.
Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph
Graph neural networks (GNNs) are deep learning models designed specifically for graph data, and they typically rely on node features as the input to the first layer.
Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework
With these metrics, one can easily identify meta-features with the most complementary behaviors in two classifiers, and use them to better ensemble the classifiers.
Error-bounded Approximate Time Series Joins Using Compact Dictionary Representations of Time Series
The matrix profile is an effective data mining tool that provides similarity join functionality for time series data.
Embedding Compression with Hashing for Efficient Representation Learning in Graph
When applying such type of networks on graph without node feature, one can extract simple graph-based node features (e. g., number of degrees) or learn the input node representation (i. e., embeddings) when training the network.
Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks
In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database.
Normalization of Language Embeddings for Cross-Lingual Alignment
Learning a good transfer function to map the word vectors from two languages into a shared cross-lingual word vector space plays a crucial role in cross-lingual NLP.
VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations
To aid this, we present Visualization of Embedding Representations for deBiasing system ("VERB"), an open-source web-based visualization tool that helps the users gain a technical understanding and visual intuition of the inner workings of debiasing techniques, with a focus on their geometric properties.
Merchant Category Identification Using Credit Card Transactions
In this work, we approach this problem from a multi-modal learning perspective, where we use not only the merchant time series data but also the information of merchant-merchant relationship (i. e., affinity) to verify the self-reported business type (i. e., merchant category) of a given merchant.
Towards a Flexible Embedding Learning Framework
Our proposed framework utilizes a set of entity-relation-matrices as the input, which quantifies the affinities among different entities in the database.
Multi-stream RNN for Merchant Transaction Prediction
New challenges have surfaced in monitoring and guaranteeing the integrity of payment processing systems.
Multi-future Merchant Transaction Prediction
We use experiments on real-world merchant transaction data to demonstrate the effectiveness of our proposed model.
Constrained Non-Affine Alignment of Embeddings
Embeddings are already essential tools for large language models and image analysis, and their use is being extended to many other research domains.
Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
By building time series data mining methods on top of matrix profile, many time series data mining tasks (e. g., motif discovery, discord discovery, shapelet discovery, semantic segmentation, and clustering) can be efficiently solved.
Representation Learning by Reconstructing Neighborhoods
Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering, visualization, information retrieval, and semi-supervised learning.
The UCR Time Series Archive
This paper introduces and will focus on the new data expansion from 85 to 128 data sets.
Neighbor-encoder
By reformulating the representation learning problem as a neighbor reconstruction problem, domain knowledge can be easily incorporated with appropriate definition of similarity or distance between objects.
