TESTOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for TEST (Text Embedding for Seasonality and Trend — Generating Text-Aligned Embeddings for Time Series).

Inheritance: ModelOptions → RegressionOptions<T> → TimeSeriesRegressionOptions<T> → TESTOptions<T>

How It Works

TEST generates text-prototype-aligned embeddings for time series by leveraging pretrained language model knowledge. It translates seasonal/trend patterns into text descriptions and aligns time series embeddings to these text prototypes.

Reference: Sun et al., “TEST: Text Prototype Aligned Embedding to Activate LLM’s Ability for Time Series”, 2024.

Constructors

Constructor Summary
TESTOptions() Creates options with the default values.
TESTOptions(TESTOptions<T> other) Creates a copy of another options instance.

Properties

Property Summary
FoundationModelSize ModelSize { get; set; } Preset size of the foundation model.
double AlignmentWeight { get; set; } Gets or sets the weight for text-alignment contrastive loss.
double DropoutRate { get; set; } Dropout probability applied during training.
int ContextLength { get; set; } Number of past time steps the model reads as context.
int ForecastHorizon { get; set; } Number of future time steps to forecast.
int HiddenDimension { get; set; } Width of the model’s hidden representations.
int NumHeads { get; set; } Number of attention heads.
int NumLayers { get; set; } Number of transformer layers.
int NumPrototypes { get; set; } Gets or sets the number of text prototypes for alignment.
int PatchLength { get; set; } Number of time steps in each patch the series is split into.
int TextEmbeddingDimension { get; set; } Gets or sets the text embedding dimension from the language model.