Search Results for author:
Found 22 papers, 7 papers with code
QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Version
The first difficulty in enabling continual calibration on the edge is that the full training data may be too large and thus not always available on edge devices.
TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
Next, we employ TFB to perform a thorough evaluation of 21 Univariate Time Series Forecasting (UTSF) methods on 8, 068 univariate time series and 14 Multivariate Time Series Forecasting (MTSF) methods on 25 datasets.
Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
Multi-scale division divides the time series into different temporal resolutions using patches of various sizes.
LightPath: Lightweight and Scalable Path Representation Learning
Next, we propose a relational reasoning framework to enable faster training of more robust sparse path encoders.
A Crystal-Specific Pre-Training Framework for Crystal Material Property Prediction
To overcome these challenges, we propose the crystal-specific pre-training framework for learning crystal representations with self-supervision.
LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version
First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model.
A Pattern Discovery Approach to Multivariate Time Series Forecasting
To capture the temporal and multivariate correlations among subsequences, we design a pattern discovery model, that constructs correlations via diverse pattern functions.
AutoPINN: When AutoML Meets Physics-Informed Neural Networks
We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.
Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting
To overcome these limitations, we propose SEARCH, a joint, scalable framework, to automatically devise effective CTS forecasting models.
A Comparative Study on Unsupervised Anomaly Detection for Time Series: Experiments and Analysis
The continued digitization of societal processes translates into a proliferation of time series data that cover applications such as fraud detection, intrusion detection, and energy management, where anomaly detection is often essential to enable reliability and safety.
RetroGraph: Retrosynthetic Planning with Graph Search
We observe that the same intermediate molecules are visited many times in the searching process, and they are usually independently treated in previous tree-based methods (e. g., AND-OR tree search, Monte Carlo tree search).
Ranked #2 on
Multi-step retrosynthesis
on USPTO-190
Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version
(i) Linear complexity: we introduce a novel patch attention with linear complexity.
Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version
This is an extended version of "Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection", to appear in IEEE ICDE 2022.
Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version
In this setting, it is essential to learn generic temporal path representations(TPRs) that consider spatial and temporal correlations simultaneously and that can be used in different applications, i. e., downstream tasks.
Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version
Such spatio-temporal agnostic models employ a shared parameter space irrespective of the time series locations and the time periods and they assume that the temporal patterns are similar across locations and do not evolve across time, which may not always hold, thus leading to sub-optimal results.
AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version
Specifically, we design both a micro and a macro search space to model possible architectures of ST-blocks and the connections among heterogeneous ST-blocks, and we provide a search strategy that is able to jointly explore the search spaces to identify optimal forecasting models.
Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version
To improve accuracy, the ensemble employs multiple basic outlier detection models built on convolutional sequence-to-sequence autoencoders that can capture temporal dependencies in time series.
Unsupervised Path Representation Learning with Curriculum Negative Sampling
In the global view, PIM distinguishes the representations of the input paths from those of the negative paths.
Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version
For example, speed sensors are deployed in different locations in a road network, where the speed of a specific location across time is captured by the corresponding sensor as a time series, resulting in multiple speed time series from different locations, which are often correlated.
Recurrent Multi-Graph Neural Networks for Travel Cost Prediction
Origin-destination (OD) matrices are often used in urban planning, where a city is partitioned into regions and an element (i, j) in an OD matrix records the cost (e. g., travel time, fuel consumption, or travel speed) from region i to region j.
Correlated Time Series Forecasting using Deep Neural Networks: A Summary of Results
To enable accurate forecasting on such correlated time series, this paper proposes two models that combine convolutional neural networks (CNNs) and recurrent neural networks (RNNs).
Learning to Route with Sparse Trajectory Sets---Extended Version
In the second step, we exploit the above graph-like structure to achieve a comprehensive trajectory-based routing solution.
