- Rating
- 3
- Confidence
- 3
- Informativeness
- 3(+1)
- Presentation
- 3(+1)
- Soundness
- 2
Read review
Paper summary
The paper proposes a conditional diffusion framework for four time-series tasks. Two components are introduced. RACP makes the forward process trainable by replacing its mean with a learned time-dependent projection, following a similar idea to CN-Diff. R-DiT replaces the MLP sublayer of a DiT block with a rational KAN layer using a Safe Padé denominator. The framework is evaluated on forecasting (8 datasets), imputation (6), classification (10, UEA) and anomaly detection (5), with ablations on both components and additional sensitivity, efficiency and significance analyses.
Critical strengths
-
The empirical scope is unusually broad and is the main reason I lean toward acceptance. One framework is evaluated on 29 dataset–task combinations against 39 forecasting, 16 imputation, 13 classification and 18 anomaly baselines. Very few diffusion papers in this area attempt even two of the four tasks.
-
The bookkeeping in the results tables is mostly sound. I replayed every rank in Tables 2, 3 and 5 against the printed values and found no rank that violates monotonicity, and the average ranks in Tables 3 and 5 are correct. The model has the best average rank on all four tasks.
-
There is no target leakage in the sampling procedure. Algorithm 2 evaluates RACP on the predicted , not on the ground truth, which is the obvious failure mode for a learned forward process and the authors avoid it.
-
The derivations in Eqs. 10–12 check out. I verified them independently and they are correct to machine precision.
-
The model is small (0.5M parameters) and the code is released. A compact deterministic diffusion model that is competitive on four tasks is a useful artifact.
Critical weaknesses
- The two ablation tables contradict each other, so the contribution of RACP is never quantified. Table 7 reports Weather forecasting MSE of 0.6960 without RACP and 0.2930 with it, which reads as a 57.9% share. Table 8 reports the same comparison as 0.325 (DiT + MLP) and 0.308 (R-DiT + MLP) against 0.293 with RACP, a 1.5% to 4.9% share. The with-RACP rows agree exactly across the two tables (0.2930 and 0.293), so the conflict is localised to the no-RACP configuration. Table 2 corroborates the small number: the authors' own non-rational conditional diffusion reimplementation, CnDiff*, reaches 0.405 on ETTh1 against the full model's 0.4015, a 1.0% gap, while Table 7 implies a 57.7% gap on the same dataset. Either one table is wrong, or "w/o RACP" in Table 7 is not the same configuration as "MLP projection" in Table 8, in which case Table 7 does not isolate RACP at all. As it stands the second contribution is not supported by its own evidence.
- The objective as printed is not a valid variational bound, and nothing prevents the learned forward process from encoding the target. The reconstruction term in Eq. 3 sums over all rather than taking the term, and the Appendix C.2 joint carries an additional product of , so the expression is unnormalised. This matters more than a typo, because is trained jointly with on the same objective. An information-preserving projection with is exactly representable in the Safe Padé basis, and it would cut the reconstruction loss while breaking the match with the inference prior . The only term anchoring the forward process to that prior is the prior KL, which is weighted by . At the paper's own settings that weight is 0.031 for and about for . Nothing in the training constrains or monitors this. I am not claiming the model does exploit it, and the reported results suggest it does not, but a paper whose central mechanism is a trainable forward process needs either a proper bound or an explicit constraint and a diagnostic.
- The novelty framing overstates the gap on both components. The Abstract and Introduction describe existing forward processes as fixed and non-trainable, but the related work correctly credits CN-Diff [1] with non-linear learnable transformations and learnable conditions in the forward process for time-series forecasting. The Introduction's premise therefore contradicts the paper's own related work. Trainable or data-dependent forward processes are also well established outside time series, for example variational diffusion models [7], cold diffusion [8] and blurring diffusion [9], none of which is cited. On the architecture side, placing KAN layers in transformers is already done by KAT and the temporal KAN transformer, so the delta is the rational basis [4, 5, 6] inside a diffusion denoiser. The claim of being the first diffusion framework to be state of the art on all four tasks is also stronger than the evidence. TimeDiT [2], which the paper cites, already covers three of the four, and unified multi-task models such as UniTS (arXiv:2403.00131) cover all four in one model.
Minor issues
- Table 6's statistic is never defined. The caption reports Mean, Median, Std, P95 and Max of some per-window quantity before and after the RACP projection, but the text uses the table to support the correlation claim in both directions, since Electricity rises from 0.5888 to 0.8800 while SMAP falls from 0.9482 to 0.7684.
- In Table 2, eight models print 0.016 on Exchange and receive ranks 2,2,2,2,2,2,8,9. Seventeen columns across Tables 2 and 3 have this property, and the tie convention is not applied consistently even within one column.
- Table 22's average rank of 2.2 reproduces exactly from the accuracy columns alone, but the surrounding text implies it covers accuracy, recall and precision. Over all three the value is 3.80.
Questions for authors
Please refer to weaknesses for details.
5 comments
Response to Reviewer Mb1x
Step 4: Variational bound, which is exactly Eq. (3).
Using as the variational posterior and applying Jensen's inequality,
The numerator (Eq. 13) and the denominator (Step 1) are factorized over the same steps in the same direction, so the log-ratio splits term by term:
$ + \underbrace{\sum_{t=2}^{T} \mathbb{E}_{q_\phi} D_{\mathrm{KL}}\big(q_\phi(x^{t-1} \mid x^t, x, c),|,p_\theta(x^{t-1} \mid x^t, c)\big)}_{\mathcal{L}_{\text{diff}}}$
This is exactly Eq. (3), with the diffusion sum indexed from . The bound holds for every . This structure is already established in state-space models [4]: over the diffusion steps, Eq. (13) has an initial state, Markov transitions and an emission at every step, and the bound above is the standard variational objective of deep state-space models
Relation to the standard data likelihood. The sampler outputs . By the chain rule,
The first term is the usual data likelihood. The second is a consistency term on the intermediate predictions, bounded above by for fixed-variance Gaussian emissions. Hence
so Eq. (3) also bounds the standard negative log-likelihood, up to a constant independent of and .
Target-information leakage and prior matching.
We agree that a learnable forward process could potentially retain target information in the final diffusion state. However, such behavior is penalized by the prior KL term. Specifically, for , the exact prior KL is
$ \mathcal{L}_{\mathrm{prior}} =D_{\mathrm{KL}}\left( q_\phi(x^T\mid x,c),|,p(x^T\mid c) \right)$
$\mathcal{L}_{\mathrm{prior}} =\frac{1}{2}\left[ |\delta_T(x,c)|_2^2 +d\left(-\bar{\alpha}_T-\log(1-\bar{\alpha}_T)\right) \right], $
where $ \delta_T(x,c)= \sqrt{\bar{\alpha}_T}\operatorname{RACP}_\phi(x,T) +\left(\sqrt{1-\bar{\alpha}_T}-1\right)c. $
Thus, the small value of does not eliminate the penalty for a fixed displacement of the final-state mean from the inference prior. In particular, for the information-preserving construction , the mean-dependent KL becomes $ \frac{1}{2} \left| x+\left(\sqrt{1-\bar{\alpha}_T}-1\right)c \right|_2^2, $ which does not vanish as . We emphasize that the prior KL penalizes, rather than strictly prohibits, target-information retention.
Empirical diagnostic.
To assess whether the trained model exhibits the proposed information-preserving behavior, we measured the final-state prior KL per dimension and the relative projection norm . The results are summarized below.
| Dataset | Prior KL/dim | Projection norm ratio |
|---|---|---|
| ETTh1 | ||
| ETTm1 | ||
| MSL | ||
| SMAP |
The learned projection norm ratios (--) are substantially below the amplification factor required by the specific construction identified by the reviewer. The small prior KL values further indicate that the learned final-state distributions remain close to the inference prior. Although these diagnostics cannot exclude every form of target-information leakage, they provide evidence against the particular amplification mechanism raised in the review.
Response to Reviewer Mb1x
Weakness 3: The novelty framing four in one model.
We emphasize that our novelty is not these ingredients (learnable nonlinear diffusion, rational functions) individually, but their specific parameterization and integration within conditional diffusion for multivariate time-series analysis (forecasting, classification, imputation and anomaly detection). The integration is not a "trivial engineering exercise", rather it is a grounded research contribution that advances the state of the art. We further clarify the distinction and provide matched evidence. We revised the Abstract, Introduction, and Related Work to clarify these distinctions and avoid overstating novelty.
1. Novelty of the forward process.
We acknowledge that modifying or learning the forward diffusion process is not new in itself. Variational Diffusion Models (VDM) optimize the noise schedule, Cold Diffusion considers alternative degradation operators such as blurring and masking, and Blurring Diffusion Models introduce structured blurring-based corruption. NDM and CN-Diff further demonstrate learnable nonlinear transformations, with CN-Diff applying such transformations to time-series forecasting. We will explicitly discuss these works and correct the Introduction's characterization of prior forward processes as universally fixed and non-trainable.
Our contribution is therefore not the introduction of a trainable forward process per se, but the
Rational Adaptive Correlation Projection (RACP): a learnable, time-dependent rational-function transformation within the conditional forward diffusion process, designed to capture inter-feature dependencies in multivariate time series. Unlike approaches primarily concerned with learning noise schedules or specifying alternative corruption operators, RACP directly parameterizes the data transformation through rational functions. Relative to CN-Diff, we investigate this rational parameterization and extend its application beyond forecasting to imputation, anomaly detection, and classification.
The benefit of this specific parameterization is evaluated in Table 8. With the R-DiT denoiser fixed, replacing the MLP forward projection with RACP improves Weather forecasting MSE from 0.308 to 0.293, ETTm2 imputation MSE from 0.034 to 0.014, SWaT anomaly detection F1 from 87.35 to 90.16, and PEMS-SF classification accuracy from 0.844 to 0.898. These results provide direct evidence for the benefit of rational projection over an MLP alternative in the evaluated configurations.
2. Novelty of the denoising architecture.
We agree with the reviewer that incorporating KAN layers into transformers is not new. In particular, KAT already introduces rational basis functions into transformer architectures, while temporal KAN-based transformers investigate such functional representations for time-series modeling.
We clarify that the contribution of R-DiT is not the invention of rational KAN layers or their use in transformers, but their integration into a diffusion denoising architecture for time-series analysis, together with timestep-dependent conditioning and the proposed RACP forward process.
Table 8 provides controlled evidence for R-DiT. With the projection type fixed, R-DiT improves upon conventional DiT across all four evaluated tasks, under both MLP and RACP projections.
To further examine whether a rational KAN-based transformer without diffusion can account for the performance of RAF-Diff, we additionally evaluated a non-diffusion Transformer equipped with rational KAN layers (KAT-style).
Table: Comparison between a non-diffusion rational KAN Transformer (KAT-style) and RAF-Diff across four tasks.
| Task | Dataset | KAT-style | RAF-Diff |
|---|---|---|---|
| Forecasting (MSE ) | ETTh1 | 0.624 | 0.401 |
| ETTm1 | 0.764 | 0.338 | |
| Exchange | 0.056 | 0.016 | |
| Imputation (MSE , 25% mask) | ETTh1 | 0.104 | 0.052 |
| ETTm1 | 0.026 | 0.021 | |
| Anomaly Detection (F1 ) | MSL | 83.58 | 89.74 |
| SMAP | 71.03 | 91.84 | |
| Classification (Acc. ) | UWave | 0.859 | 0.884 |
RAF-Diff outperforms this non-diffusion rational KAN Transformer across the evaluated datasets, including substantial improvements on ETTm1 forecasting (0.764 to 0.338) and SMAP anomaly detection (71.03 to 91.84).
We emphasize that this additional comparison evaluates the effectiveness of the complete RAF-Diff framework relative to a non-diffusion rational KAN Transformer, rather than isolating the effect of a single component. The component-level contributions of RACP and R-DiT are more directly evaluated through the controlled comparisons in Table 8.
Together, these experiments support the value of combining rational-function-based forward projection and denoising within a conditional diffusion framework.
Response to Reviewer Mb1x
Weakness 1: The two ablation tables ⋯ its own evidence.
Response: Tables 7 and 8 evaluate two different aspects of the proposed forward projection, rather than the same ablation configuration.
Table 7 evaluates the contribution of the learnable forward transformation relative to an identity mapping. Specifically, in the "w/o RACP" configuration, we replace the RACP transformation with an identity mapping, i.e., (RACPϕ(x,t)=x) (DDPM), while retaining the remaining forward diffusion formulation. Thus, this experiment compares the proposed learnable rational transformation against a non-learnable identity transformation. On Weather, the forecasting MSE decreases from 0.6960 to 0.2930, while on ETTh1, it decreases from 0.9495 to 0.4015. These results quantify the performance improvement obtained by replacing the identity transformation with RACP.
Table 8 isolates the additional benefit of rational parameterization over a conventional learnable MLP projection. Unlike Table 7, both configurations retain a learnable forward transformation, differing only in its parameterization. With the R-DiT denoiser fixed, replacing MLP with RACP reduces Weather forecasting MSE from 0.308 to 0.293 (4.87%) and ETTm2 imputation MSE from 0.034 to 0.014 (58.82%). Similarly, SWaT anomaly detection F1 improves from 87.35 to 90.16, and PEMS-SF classification accuracy increases from 0.844 to 0.898. These results directly quantify the additional benefit of the proposed rational projection over the learnable MLP alternative.
Regarding CnDiff in Table 2, this baseline is distinct from the identity-mapping ablation in Table 7. CnDiff already employs a learnable nonlinear transformation in its forward process, whereas Table 7 uses a fixed identity transformation as the baseline. Consequently, the relatively small difference between CnDiff (0.405) and RAF-Diff (0.4015) on ETTh1 does not contradict the larger performance improvement observed relative to the identity mapping. Rather, these experiments evaluate different baselines: a fixed identity transformation, a learnable MLP projection, and an existing nonlinear transformation-based diffusion model.
Weakness 2: The objective as printed ⋯ and a diagnostic.
We update Eq.(13) to its normalized version as follows. However, we emphasize that the loss term remains the same, only the way the joint is written changed.
Step 1: Non-Markovian forward process. From Eq. (1), the forward marginals are qϕ(xt∣x,c)=N(αˉtRACPϕ(x,t)+(1−αˉt)c(1−αˉt)I).
As shown in the corrected Eqs. (5)-(6), the transition qϕ(xt∣xt−1,x,c) depends on the data x directly, through RACPϕ(x,t)−RACPϕ(x,t−1).
The forward process is therefore non-Markovian, and following DDIM [1] we write it as qϕ(x1:T∣x,c)=qϕ(xT∣x,c)∏t=2Tqϕ(xt−1∣xt,x,c). Unlike in DDPM, where the data enters only the first forward step, here x enters every forward transition.
Step 2: Generative joint in Normalized Form (Eq.~13).
For time series diffusion models, forecasting xθ has been found to be more effective than predicting ϵθ [2,3]. Our denoiser therefore predicts the clean series x^θ(xt,t) from every noisy state, and each reverse step is built on this prediction, pθ(xt−1∣xt,c)=qϕ(xt−1∣xt,x^θ(xt,t),c) (Eq.~16). Because x enters every forward transition, the generative process mirrors this with a link back to the data at every step. Each such link generates its own auxiliary variable x~(t): $ p_\theta\big(x^{1:T}, \tilde x^{(1:T)} \mid c\big) = p(x^T \mid c)\prod_{t=2}^{T} p_\theta(x^{t-1} \mid x^t, c);\prod_{t=1}^{T} p_\theta\big(\tilde x^{(t)} \mid x^t, c\big), \qquad p_\theta\big(\tilde x^{(t)} \mid x^t, c\big) = \mathcal{N}\big(\hat x_\theta(x^t, t), \sigma^2 I\big). $
The reverse chain now ends at x1 (since qϕ(x0∣x1,x,c) has zero variance), and each auxiliary variable x~(t) is generated exactly once by a normalized conditional. Integrating out x~(1),…,x~(T), then x1,…,xT−1, then xT gives one at every step, so the joint is normalized. In particular, no density is squared at t=1.
Step 3: Likelihood. During training, every auxiliary variable is observed to equal the data, x~(1)=⋯=x~(T)=x. Our goal is to maximize pθ(x~(1:T)=x∣c)=∫pθ(x1:T,x~(1:T)=x∣c)dx1:T, which is intractable, so we maximize a variational lower bound on it.