- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper considers long-tailed time series generation and introduces E2T-DiT framework that separates discrete tail occurrence from continuous trajectory generation. A segment conditioned Axial Diffusion Transformer is used to generate complete multivariate trajectories conditioned on the sampled state sequence. It further introduces a state balanced denoising objective and penalty to strengthen learning on rare temporal states while preserving the empirical occurrence distribution learned by the separate state planner. While the paper addresses an interesting problem, I find that the current formulation, experimental design, and presentation do not provide sufficiently convincing evidence for its main claims.
Critical strengths
- The paper targets an important problem called rare temporal behavior generation in time series. The separation between state occurrence and trajectory realization is intuitively reasonable and could potentially be useful.
Critical weaknesses
-
The experiment evaluation does not validate the core contribution. The paper is motivated by long tail generation and rare episodes, but the primary comparison in Table 1 relies on conventional metrics that are not specifically designed to measure rare state or rare episode fidelity. More importantly, the method explicitly claims to model several features including state occurrence, episode duration and lower/upper tail prevalence, yet it does not report baseline comparison for any of these quantities.
-
The “temporal rarity dilution” is not convincingly demonstrated. The argument that the same rare episode appears in more overlapping windows as increases is intuitive, but no controlled experiment isolates this effect. While some baselines perform worse for larger windows and the paper interprets it as support for temporal rarity dilution, longer sequences are intrinsically more difficult to model due to increased temporal dependency length and higher dimensionality. Therefore, deterioration with larger does not uniquely support the proposed hypothesis.
Questions for authors
-
What is the direct evidence that E2T-DiT generates rare episodes better than DLTTS and other baselines? Please provide more metrics on baseline comparisons rather than only global generation metrics.
-
What exactly are , , and for SWaT? The paper defines SWaT tail points using attack labels, which does not seem compatible with Eq. (1) and the boundary consistency objective.
-
What motivates the threshold of oil temperature for ETTh1 and ETTm1? Is this based on domain knowledge or empirical quantile? How sensitive are the results to the threshold hyperparameter?
-
Can the authors provide a more direct empirical validation of temporal rarity dilution? The performance degradation for longer windows could arise simply from difficult in long sequences modeling.
-
Are the results averaged over multiple runs? Table 1 reports single values and I could not find variance or confidence intervals. Given the stochasticity of generative training and metrics, uncertainty results would help assess whether relatively small improvements are statistically reliable.
-
Could the authors provide comparisons with recent methods such as [1][2][3]? The baseline comparison appears somewhat outdated and incomplete. The improvements over older baselines do not necessarily demonstrate competitiveness against the current methods.
[1] Population aware diffusion for time series generation.
[2] DiM-TS: Bridge the Gap Between Selective State Space Models and Time Series for Generative Modeling.
[3] TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective.