CompleMatch:時系列半教師あり分類の時間周波数相補性をブーストする
IEEE transactions on pattern analysis and machine intelligence
|December 15, 2025
まとめ
CompleMatchは、時間領域と周波数領域のデータを組み込むことにより、時系列半教師あり分類(SSC)を強化します。この新しいアプローチは、ラベル付きデータが限られている場合にモデルの精度を向上させ、既存の方法よりも優れたパフォーマンスを発揮します。
科学分野:
- 機械学習
- データサイエンス
- 信号処理
背景:
- 半教師あり分類(SSC)は、ラベル付きサンプルが少ない場合にモデルのパフォーマンスを向上させるために、ラベルなしデータを活用します。
- 既存の時系列SSC法は、主に時間的依存性に依存していますが、これはノイズに敏感であり、グローバル特徴の周期性を逃す可能性があります。
研究 の 目的:
- 時間領域と周波数領域の両方からの相補的な情報源を利用する新しい時系列SSCフレームワークであるCompleMatchを導入します。
- 多様なデータ表現を統合することにより、ラベルなしデータからの学習を強化します。
主な方法:
- CompleMatchは、時間領域と周波数領域のビューを持つ2つの同時に訓練されたディープニューラルネットワークを使用した共同訓練パラダイムを採用しています。
- ラベル伝播によって生成された疑似ラベルは、時間周波数表現の相補的な性質を利用して、各ネットワークのトレーニングをガイドします。
- 時間周波数対照学習モジュールは、疑似ラベルの品質と表現の識別性を向上させるために、教師あり信号と自己教師あり信号を統合します。
主要な成果:
- CompleMatchは、時系列SSCタスクにおいて最先端の方法よりも大幅に優れたパフォーマンスを発揮します。
- 因子分解研究と視覚化は、提案された時間周波数相補学習戦略の有効性を確認します。
- このフレームワークは、特にラベル付きデータが限られている条件下で、堅牢性とパフォーマンスを向上させます。
結論:
- 提案されたCompleMatchフレームワークは、堅牢な時系列SSCのために相補的な時間的および周波数的情報を効果的に活用します。
- 多様なデータ表現と対照学習の統合は、モデルのパフォーマンスと識別力を向上させます。
- CompleMatchは、時系列分析における半教師あり学習のための有望な進歩を提供します。
関連する概念動画
Frequency-dependent Selection
23.0K
When the fitness of a trait is influenced by how common it is (i.e., its frequency) relative to different traits within a population, this is referred to as frequency-dependent selection. Frequency-dependent selection may occur between species or within a single species. This type of selection can either be positive—with more common phenotypes having higher fitness—or negative, with rarer phenotypes conferring increased fitness.
23.0K
Expected Frequencies in Goodness-of-Fit Tests
7.0K
A goodness-of-fit test is conducted to determine whether the observed frequency values are statistically similar to the frequencies expected for the dataset. Suppose the expected frequencies for a dataset are equal such as when predicting the frequency of any number appearing when casting a die. In that case, the expected frequency is the ratio of the total number of observations (n) to the number of categories (k).
7.0K
Classification of Signals
1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K
Properties of Fourier Transform II
697
The Fourier Transform (FT) is an essential mathematical tool in signal processing, transforming a time-domain signal into its frequency-domain representation. This transformation elucidates the relationship between time and frequency domains through several properties, each revealing unique aspects of signal behavior.
The Frequency Shifting property of Fourier Transforms highlights that a shift in the frequency domain corresponds to a phase shift in the time domain. Mathematically, if x(t) has...
The Frequency Shifting property of Fourier Transforms highlights that a shift in the frequency domain corresponds to a phase shift in the time domain. Mathematically, if x(t) has...
697
Aliasing
523
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
523
Aggregates Classification
950
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
950


