- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper introduces Equivariant Neural Forecaster (ENF), an architecture that targets multivariate time-series forecasting robust to channel permutations and capable of creating artifacts containing channel-wise interactions. While the underlying motivation is interesting, the paper suffers from significant presentation and clarity issues. The text is very dense, written with a lot of jargon and synonyms, and lacks clarity. Its comprehension requires significant effort on the reader side. Furthermore, the empirical evaluation is limited and insufficient, lacks comparison to state-of-the-art methods, and fails to provide a clear explanation of the proposed forecasting mechanism and its training. In my view, a complete rewrite is required to make this work publishable, and thus, I recommend rejection.
Critical strengths
- The motivation behind creating an artifact that captures cross-channel interactions is compelling and appears somewhat novel. ENF appears to achieve this goal.
Critical weaknesses
- Clarity, presentation, and notation
- There is a mismatch between the title on OpenReview and the title in the PDF. Notably, the title in the PDF contains “Irreducible Representations”, which do not appear in the paper.
- Figure 1 is poorly formatted with overlapping text and arrows.Figure 2 is difficult to read. ENF layer structure is unclear, and a visualization of the end-to-end flow would be much more helpful. Many elements in the plot appear to be arbitrary (e.g., the grey arrow from "double center" to "channel updates”).
- The paper uses numerous competing synonyms and technical jargon that are never properly introduced or defined. A few examples: endpoint effects/dependencies, shared-value attention, bilateral coupling, decomposing states into a shared consensus and zero-mean deviations, shared and identity-conditioned feed-forward networks, bilinear content field.
- Undefined variables/notation issues.
- E used in B is undefined.
- and are never defined
- , , , , are all undefined or unclear in their context.
- Theorem 1: RevIN acronym hasn’t been defined. While it comes from Kim et al. 2022, which has been cited earlier, the acronym hasn’t been introduced.
- L356: (d64/L1) notation is undefined.
- L373: First-order EQNN is never defined, and we cannot deduce what this baseline represents.
- Methodology.
- The complexity of the method seems unnecessary. In L151, the authors claim that a naive neural network is coordinate-dependent. However, a simple Transformer without positional encodings and with channel-wise normalization also preserves channel permutation invariance. The definition of the “Architectural Constraint” appears to unnecessarily decouple normalization parameters from the sensor identity table, as the logical order of operations should be permuting channels first, then computing normalization statistics.
- The paper lacks a description of the actual forecasting mechanism. It is unclear whether the architecture is trained with a next-token or a direct-prediction objective.
- Experiments.
- Evaluation on traffic (PEMS) benchmarks is insufficient, and Q1 is not sufficiently evaluated. While the experimental setup mentions PEMS{03,04,07,08}, Electricity, Solar, Weather, ETTh1/2, ETTm1/2, and Exchange rates, Table 1 contains PEMS results only. Figure 3 contains a selection of these datasets, but not all of them. I find this quite surprising and unsatisfactory.
- The paper strongly emphasizes comparing its results with iTransformer, which is misguided. iTransformer has been published in 2023, and since then numerous stronger baselines have appeared. A short and non-representative list of published and highly cited methods is: CycleNet (Neurips 2024) [1], TQNet (ICML 2025) [2], DUET (KDD 2025) [3]. Moreover, in the analysis of the results, there are several errors: the authors comment on short-term forecasting vs multi-step predictions suffering from error propagation, yet no forecasting mechanism has been introduced in the paper; we also do not know whether the architecture is trained with a next-token or direct prediction objective.
- The authors should focus on a set of the most imporant results because the current evaluation section simply packs too many experiments and does not explain any of them sufficiently. All paragraphs just send the reader to the Appendix, and as a result, none of the four posed questions are thoroughly explored.
- Related work and lack of comparison to baselines that focus on forecasting with channel-wise permutation invariance. A paper published on ICLR 2026 (CPiRi [4]) appears to explore a very similar problem and has not been mentioned in the related work nor compared to in the experiments.
[1] Lin et al. 2024 “CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns”, NeurIPS https://neurips.cc/virtual/2024/poster/94391
[2] Lin et al. 2025 “Temporal Query Network for Efficient Multivariate Time Series Forecasting”, ICML https://proceedings.mlr.press/v267/lin25e.html
[3] Qiu et al. 2025 “DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting”, KDD https://doi.org/10.1145/3690624.3709325
[4] Xu et al. 2026 “CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting”, ICLR https://arxiv.org/abs/2601.20318v1
Reply to Reviewer 6xnx — Original submission and presentation (1/3)
Dear Reviewer 6xnx,
Several primary grounds cited for rejection rest on verifiable factual inaccuracies regarding material already present in the submitted manuscript, alongside two methodological misconceptions regarding normalization parameters and equivariant relational modeling. We establish the factual record from the submitted PDF first, address the methodological misconceptions and ENF’s core novelty second, and present new comparisons against recent baselines (
TQNet,CycleNet) and controlled ablations third.1. Corrections to the Factual Record (Submitted Manuscript)
Nine specific items described in the review as missing, undefined, or arbitrary were explicitly defined and reported in the original submission:
"CPiRi has not been mentioned in the related work" — Incorrect:
CPiRi(Xu et al., 2026) was explicitly discussed in Section 2 (lines 111–112) and cited in References (lines 592–593). Not evaluatingCPiRinumerically is a separate point that we explicitly note in revised Section 4.1."Figure 3 contains a selection of these datasets, but not all of them... Q1 is not sufficiently evaluated" — Full benchmark already provided: The Figure 3 caption (lines 411–413) explicitly directed readers to Appendix Table 10 (lines 1089–1107), which reported the complete 13-dataset benchmark across all listed datasets. Revised Section 4.2 now links the compact summary directly to the full 13-dataset panels (Appendix Tables 15 and 22).
"E used in B is undefined" — Incorrect: The sensor identity table E∈RC×de was defined in Section 3.1 (lines 133–135 and 154–156), and its centered form Estd=PstdE was defined immediately inside the definition of B(Estd,D) in Section 3.2.3 (lines 266–268).
"o1 and o0 are never defined" — Incorrect: Equation (6) in Section 3.2.3 (lines 270–275) explicitly defined (os)i=Wo∑j=1C(As)ij(vj+mij) for s∈{0,1}, immediately followed by δ=Pstd(o1−o0).
"L356:
(d64/L1)notation is undefined" — Incorrect: Section 4.1 (lines 342–343) explicitly defined the compact setup as (d=64,L=1)."L373: First-order EQNN is never defined" — Incorrect: Lines 373–374 defined
First-order EQNNat that exact locus ("updates channel states via attention without second-order pair fields"), and Appendix B.1 (lines 817–819) listed all retained components."
Irreducible Representationsdo not appear in the paper" — Incorrect: Section 3.2.1 (lines 199–204) explicitly decomposed the channel space RC under SC into the 1D trivial and (C−1)D standard irreducible representations, while Appendix Table 3 and Appendix A.3 (lines 760–773) explicitly distinguished those from the reducible (C−1)2 pair-interaction subspace."Grey arrow from 'double center' to 'channel updates' appears arbitrary" — Route explicitly specified: Figure 2b explicitly labeled this route
g, r, c -> channel updates(line 173), matching Section 3.2.2 (lines 242–244: "the single-variable terms (g,r,c) are routed into channel state accumulators") and Appendix B.2 Step 1 (lines 827–829)."Technical jargon never introduced or defined" — Incorrect: The cited concepts were specified in the following passages: global consensus μ=C11⊤h and zero-mean deviations D=Pstdh (1⊤D=0) in §3.2.1 (lines 201–210); additive endpoint effects (g,ri,cj) vs. bilateral residual R⊥=PstdRPstd in Eq. (3) (§3.2.2, lines 228–236); shared-value attention (vj identical across receivers vs. target-conditioned vj+mij) in Figure 1b and §3.2.3 (lines 248–257); bilinear content field in Eqs. (2) and (4); and shared vs. identity-conditioned FFNs in §3.2.3 (lines 279–280) and Appendix B.2 Step 4 (lines 846–848).
Targeted presentation improvements in the revision: Where presentation genuinely benefited from tightening, we expanded
RevINat first mention (§3.1), labeled projection matrices Wh,Wa,Wb,W×,Wo inline (§3.2.2–3.2.3), adjusted Figure 1’s arrows to remove overlaps, placed the direct decoder and explicit MSE objective together in §3.2.3 (Eq. 8), and reorganized Section 4 around self-contained main-text tables (Tables 1–7).