- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Relational Adaptive Flow (RAFlow) is a multivariate time-series anomaly detection method, built upon graph-conditioned continuous normalizing flows. It introduces window-adaptive relational context, entity-specific Gaussian priors, kinetic-energy regularization, and path-integral anomaly scoring.
Critical strengths
- Reframing relational anomaly detection as assessing both conditional density and trajectory energy, rather than relying on likelihood alone, is fancy.
- Using AUC-PR and VUS-PR makes the evaluation more informative than relying on point-adjusted detection metrics.
Critical weaknesses
-
The discrete-flow baseline uses substantially fewer parameters than RAFlow, so the headline gain may reflect increased model capacity rather than better flow dynamics.
-
The obvious alternative of conditioning every discrete-flow layer on the same relational context is insufficiently specified, leaving the core premise unresolved.
-
Ablation only partly validates the paper’s story, leaving unclear whether the training regularizer, not the trajectory-energy score, drives most of the performance.
-
The method’s central stability guarantee presupposes that Gaussian log-density is globally one-Lipschitz, so it fails even for identity flows and remains invalid in exactly the simple cases that its assumptions explicitly allow.
-
Graph & Discrete Flow comparison relies on baselines from 2020–2023, leaving it unclear whether the reported gains hold against more recent methods.
-
Case studies mainly illustrate smoother scores rather than clearer anomaly separation and raise concerns about possible false positives.
Questions for authors
Q1. Could you clarify how the conditional consistency argument is justified when anomalous windows need not remain separated after context construction?
Q2. I’m curious whether trajectory energy gives anything beyond ordinary regularization in this setting. It is presented as an additional anomaly signal, but the reported ablation does not separate its training and scoring roles.
6 comments
Response to Reviewer CHHK — Theorem 1 and Proof Steps (i)–(v)
Notation. is the number of entities,
\phi_\theta=\sum_k\phi_{k,\theta},$$ and $$\widetilde{\mathcal L}_N(\theta)=\frac{1}{NK}\sum_{c=1}^N\phi_\theta(X^c).$$ $\mathcal D\subset\mathbb R^{K\times T}$ is a compact set containing the supports of $P_N$ and $P_A$. **Theorem 1 (conditional anomaly score consistency)** **Regularity and mixing** (a) $\Theta$ is compact, $P_N,P_A$ are supported in $\mathcal D$, and $(\theta,X)\mapsto\phi_\theta(X)$ is continuous on $\Theta\times\mathcal D$. (b) The normal windows $X^1,\dots,X^N$ are strictly stationary with $\alpha$-mixing coefficients $\alpha(h)$ satisfying $\sum_{h\ge1}\alpha(h) < \infty$. **Identifiable minimiser** $\mathcal R(\theta)=\frac{1}{K}\mathbb E_{P_N}[\phi_\theta(X)]$ has a unique minimiser $\theta^\ast$ with $$\inf_{\\|\theta-\theta^\ast\\|\ge\epsilon}\mathcal R(\theta) > \mathcal R(\theta^\ast)$$ for all $\epsilon > 0$. **Score separation** There are $\tau\in\mathbb R$, $m > 0$ with $$P_N(\phi_{\theta^\ast}\le\tau)=1 \quad\text{and}\quad P_A(\phi_{\theta^\ast}\ge\tau+m)=1.$$ **Theorem** Under the three assumptions above (and the Lipschitz Assumption of the paper, which makes the flow well defined), let $$\widehat\theta_N\in\arg\min_\Theta\widetilde{\mathcal L}_N.$$ Then (i) $$\sup_{X\in\mathcal D}|\phi_{\widehat\theta_N}(X)-\phi_{\theta^\ast}(X)|\to0$$ in probability, and (ii) for $X_A\sim P_A$, $X_N\sim P_N$: $$\mathbb P\bigl(\phi_{\widehat\theta_N}(X_A)\ge\phi_{\widehat\theta_N}(X_N)+m/3\bigr)\to1.$$ **Proof** Put $\widehat{\mathcal R}_N=\widetilde{\mathcal L}_N$. A minimiser exists because $\widehat{\mathcal R}_N$ is continuous on the compact set $\Theta$ (we take a measurable selection). **(i).** Since $\phi$ is continuous on the compact set $\Theta\times\mathcal D$, hence bounded, $|\phi|\le M_\phi$, and uniformly continuous. Thus $$\omega(r):=\sup\\{ |\phi_\theta(X)-\phi_{\theta'}(X)| : X\in\mathcal D,\\ \\|\theta-\theta'\\|\le r \\}$$ is nondecreasing with $\omega(r)\to0$ as $r\downarrow0$. **(ii).** Fix $\theta$ and let $Y_c=\phi_\theta(X^c)/K$, so $|Y_c|\le M_\phi/K$ and $\mathbb EY_c=\mathcal R(\theta)$. For bounded $\alpha$-mixing variables, $$|\mathrm{Cov}(Y_c,Y_{c+h})|\le4(M_\phi/K)^2\alpha(h)$$ (Ibragimov's covariance inequality). Hence $$\begin{aligned} \mathrm{Var}\Bigl(\tfrac{1}{N}\sum_cY_c\Bigr) &\le\frac{1}{N^2}\Bigl[N\tfrac{M_\phi^2}{K^2}+2\sum_{h=1}^{N-1}(N-h)\\,4\tfrac{M_\phi^2}{K^2}\alpha(h)\Bigr]\\\\ &\le\frac{M_\phi^2}{NK^2}\Bigl(1+8\sum_{h\ge1}\alpha(h)\Bigr)\xrightarrow[N\to\infty]{}0, \end{aligned}$$ so $\widehat{\mathcal R}_N(\theta)\to\mathcal R(\theta)$ in probability by Chebyshev. **(iii).** Given $\epsilon > 0$ choose $r$ with $\omega(r)/K < \epsilon/3$ and a finite $r$-net $\theta_1,\dots,\theta_J$ of $\Theta$ (compactness). For any $\theta$ pick $j$ with $\\|\theta-\theta_j\\|\le r$. Then $$|\widehat{\mathcal R}_N(\theta)-\widehat{\mathcal R}_N(\theta_j)|\le\omega(r)/K < \epsilon/3,$$ and likewise for $\mathcal R$. Therefore $$\sup_\theta|\widehat{\mathcal R}_N-\mathcal R|\le\max_{j\le J}|\widehat{\mathcal R}_N(\theta_j)-\mathcal R(\theta_j)|+\tfrac{2\epsilon}{3},$$ and the maximum over finitely many terms tends to $0$ in probability (Step 2). So $$\mathbb P\bigl(\sup_\theta|\widehat{\mathcal R}_N-\mathcal R| < \epsilon\bigr)\to1$$ for every $\epsilon > 0$. **(iv).** Fix $\epsilon > 0$, let $\eta_\epsilon=\inf_{\\|\theta-\theta^\ast\\|\ge\epsilon}\mathcal R(\theta)-\mathcal R(\theta^\ast) > 0$ (Assumption Identifiable minimiser). On the event $\\{\sup_\theta|\widehat{\mathcal R}_N-\mathcal R| < \eta_\epsilon/2\\}$, for every $\theta$ with $\\|\theta-\theta^\ast\\|\ge\epsilon$, $$\widehat{\mathcal R}_N(\theta) > \mathcal R(\theta)-\eta_\epsilon/2\ge\mathcal R(\theta^\ast)+\eta_\epsilon/2 > \widehat{\mathcal R}_N(\theta^\ast),$$ so $\theta$ is not a minimiser. Hence $\mathbb P(\\|\widehat\theta_N-\theta^\ast\\| < \epsilon)\to1$. **(v).** For $X\in\mathcal D$, $|\phi_{\widehat\theta_N}(X)-\phi_{\theta^\ast}(X)|\le\omega(\\|\widehat\theta_N-\theta^\ast\\|)$. Given $\epsilon > 0$ choose $r$ with $\omega(r) < \epsilon$; on $\\{\\|\widehat\theta_N-\theta^\ast\\|\le r\\}$ (probability $\to1$ by Step 4) the supremum over $\mathcal D$ is $< \epsilon$.Response to Reviewer CHHK — Theorem 1, Final Proof Step, and Corollary 1
Theorem 1, proof continued
(vi). Let ; . By Assumption Score separation, almost surely and with both points in . On , and , so
Therefore the probability in (ii) is at least . (The event does not involve the test points, so no independence between the training sample and the test pair is needed.)
Why support separation alone is not enough
Let and have disjoint supports at distance . Since is Lipschitz on with constant (see Proposition 1), points of within of can differ from normal scores by at most , so whenever Assumption Score separation holds, and no separation can hold for arbitrarily small . Conversely, even with a large distance, a trained density can place high mass between the clusters; then anomalies there score lower than normal points, and Assumption Score separation fails. Separation of the scalar score is therefore the quantity that matters.
Corollary 1 (entity-level separability)
Entity-level separation
For an entity there are , with , , and is continuous on .
Corollary
Under Assumptions Regularity and mixing, Identifiable minimiser, Entity-level separation:
Proof
Steps (i)–(iv) of the proof of Theorem 1 use only the training objective and give in probability. Define as in Step (i) for ; it tends to by uniform continuity on . As in Step (v),
in probability. Step (vi) with in place of gives the claim.
Detection, not localisation
The corollary concerns entity separately and says nothing about whether is the origin of the anomaly. Because depends on every entity, perturbing () changes and can change with fixed. Thus does not imply , and the entity scores should be used as a ranking of entities to inspect.
Discrete-Flow Controls, Stability, and Anomaly Scoring
Thank you for the detailed review. We corrected the parameter count, clarified the discrete controls, and revised the theoretical guarantees.
W1–W2. Capacity and conditioning every discrete layer
The SMD checkpoint has 46,569 parameters (0.047M). The original efficiency table overstated this count. Standard MTGFlow has a reported 4.1M parameters. The four residual controls and MTGFlow-small each use about 0.05M.
D-RF(M) uses M=2,4,8 untied residual layers, each conditioned on the same window context C. Each layer adds gθm(z,m/M,C)/M to the latent state and is invertible for fixed C when its residual branch is contractive. Tied Euler(2) shares one field across two updates. RAFlow trains with adaptive ODE integration and uses two tied Euler updates at inference.
Five-seed mean test AUC-PR (%).
RAFlow leads MTGFlow-small by 4.8–6.6 points and D-RF(8) by 1.8–2.4 points. D-RF(8) uses the same context at every layer and has a similar parameter count. The comparison still varies weight sharing and training integration.
W3 / Q2. Kinetic energy during training and inference
In Table 13, we train with the kinetic penalty off or on and score each checkpoint with composite NLL alone and with weighted trajectory energy added. The first four rows give five-seed mean test AUC-PR (%). Contrasts are in percentage points.
We average each main effect across the levels of the other factor. At the tested weights, the training effect is +1.2 to +2.5 points and the scoring effect ranges from −0.2 to +0.5 points. Weighted energy has 6–8% of the NLL score's standard deviation and a Spearman correlation of 0.66–0.74 with NLL. Comparison with a tuned conventional regulariser remains open.
W4. Gaussian NLL and stability
The identity-flow counterexample is correct. The standard Gaussian NLL has unbounded gradient x. Proposition 1 bounds the score on bounded inputs under regularity conditions on the velocity, its divergence, and the context map. The following comments provide the revised theorem statements, proofs, corollaries, and supporting lemmas.
W5. Recent baselines
MTGFlow-cluster (Zhou et al., IEEE TKDE 2024) scores 59.0 / 76.2 / 79.4 / 72.6 / 82.2 test AUC-PR (%) in dataset order. RAFlow leads by 1.0–2.4 points. Appendix K.7 also reports GraphTSAD at 58.4 / 75.8 / 78.8 / 71.4 / 81.8. SARAD and CATCH lead the broader benchmark on SWaT and SMAP, respectively.
W6. Test-set false alarms at matched recall
Episodes are counted per 1,000 normal windows at 80% recall. RAFlow yields 34% fewer episodes on SMD and 42% fewer on MSL than MTGFlow at this recall.
Q1. Consistency after context construction
Theorem 1 assumes a population margin in the final score, which depends on the window and its context. Under the stated assumptions, the fitted score gap is at least one-third of that margin with probability tending to one. On the test split, 20% of anomalous SMD contexts and 17% of anomalous MSL contexts fall within the 95% normal-context ellipsoid. On the validation split, the 5th percentile of anomalous scores exceeds the 95th percentile of normal scores by 0.34 on SMD and 0.40 on MSL. These quantile gaps describe the observed validation distributions.
Other corrections