- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes TED-ITS, a fine-tuning framework for long tailed industrial time series generation based on a pretrained class-conditional diffusion model. The Noise-Adaptive Target Reconstruction (NATR) probabilistically replaces the original reconstruction target with a candidate trajectory to increase supervision from minority fault samples. Moreover, the Balanced-Condition Regularization (BCR) samples auxiliary class labels uniformly and encourages predictions conditioned on the original and auxiliary labels to remain consistent in both the time and frequency domains. Experiments on fou datasets demonstrates that TED-ITS achieves superior performance compared with existing methods.
Critical strengths
-
The paper considers a practically relevant problem called imbalanced industrial fault data and improves the generation of minority operating states.
-
The author explicitly discuss limitations of their theoretical results. In particular, the theoretical section acknowledges that geometric compatibility does not imply fault semantic equivalence and that reconstruction target redistribution does not guarantee improved unconditional minority generation.
Critical weaknesses
-
The core training mechanism is conceptually inconsistent and may actively corrupt class semantics. NATR keeps the original class condition while sometimes replacing target with a sample drawn from another less frequent class . This is not merely data augmentation and it introduces contradictory conditional supervision, as there is nothing to guarantee that the classes are semantically compatible. More seriously, the theoretical analysis states that the induced reconstruction bias is not guaranteed to be small. Crucially, the experiments do not evaluate whether class semantics survive the training protocol. There is no per-class generation fidelity or analysis of whether distinct fault classes collapse toward each other.
-
The claims of label free and long tail are not convincingly supported by the evaluation. The motivation is substantially overstated as TED-ITS is not label free during training. The baseline comparison is also problematic. The baseline results in Table 1 are taken from DLTTS, rather than rerunning the competing methods under the same environment and protocol. It results in unfair comparison.
Questions for authors
-
How do the authors justify training with the original condition when NATR replaces the reconstruction target with a trajectory from a potentially different class ? Why does it not corrupt the class conditional mapping?
-
Can the authors provide per-class semantic fidelity experiments? For example, train an independent fault classifier on real data and evaluate whether samples generated under each condition remain identifiable as that fault type after fine-tuning.
-
What does label free contribute beyond ordinary classifier-free diffusion?
-
How are unconditional samples evaluated against real tail sequences? As without reporting tail prevalence and recall, a method could simply obtain high scores simply by changing how frequently tail samples are generated.
-
Why are the baseline results copied from DLTTS rather than rerun under the same protocol? I do not consider it is sufficient to establish a fair comparison.
-
Could the authors provide more comparisons with recent related methods such as [1][2][3]? The baseline comparison appears somewhat outdated and do not necessarily demonstrate competitiveness against the current methods. The downstream evaluation compare only against Diffusion-TS is also insufficient.
[1] Fide: Frequency-inflated conditional diffusion model for extreme-aware time series generation.
[2] Population aware diffusion for time series generation.
[3] DiM-TS: Bridge the Gap Between Selective State Space Models and Time Series for Generative Modeling.