- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes a gating mechanism to make the temporal representation learning robust. The motivation is that noisy data, errors, and missing observations could induce representation errors that could be amplified. Some theory is provided but is not solid enough.
Critical strengths
The motivation is clear, and the problem is valuable. Some theoretical analysis is provided.
Critical weaknesses
The literature review of the robust temporal model is limited. Some notations are not clearly explained. The theoretical analysis is not deep enough to support the gating design.
Questions for authors
- The literature review in terms of the hidden state errors seems to be limited. I am not so sure if this is the first work to observe this phenomenon and deal with this problem.
- Fig. 1 seems to be AI-generated: too many elements that are trivial and non-technical. It’s not suitable for a top-tier conference like ICLR.
- What do \mathcal{H}{hh,t}:P{t-1} and \mathcal{H}{hh,t}:\Sigma{t-1} mean in Eq. (12)? It’s not common to use colon to connect two matrix and produce a vector (since A_tb_{t-1} is a vector).
- The bold lowercase p is not defined in Eq. (14). What is binned ece?
- The theoretical analysis in Section 3.2 is not deep enough and doesn’t strongly support the gating mechanism in Eq. (3). E.g., in theory, dose the gate really control the error propagation?
- The experiments are limited. First, the author should compare the method with robust temporal models that can similarly deal with this problem with sufficient literature and citations. Second, the backbone (GRU/LTC) is not representative enough, given that we have so many sequence models. Third, more realistic datasets with noise and errors should be tested.
- I am not so sure if the three degradations in Eq. (19) are well-known and common in this domain.