- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper studies hierarchical optimal transport by proposing HiLOT. Its main contribution is largely an empirical study of how different choices in HiLOT affect OT performance.
Critical strengths
S1. Hierarchical LOT is an interesting setting. S2. Hierarchical LOT outperforms HOTT in some tasks evaluated in the experimental study.
Critical weaknesses
-
The motivation of hierarchical LOT is weak. Table 3 shows that BM25 and sentence encoder are apparently the better choice of the retieval, so why bothering optimizing hierarchical OT with LOT? There can be tasks that hierarchical OT suits best and thus HiLOT is the optimized choice but this should be elaborated more.
-
The baselines are weak. It only compares HiLOT's own variants and HOTT. Fast OT approximations should also be compared and see if it can have similar quality and performance trade-off compared to HOTT.
-
The observation regarding the orientation is largely an empirical finding, rather than ``an orientation law''.
-
The presentation needs improvement. For instance, the setup of Section 3 is brief with unnecessarily heavy use of notations without proper explanations. Section 6 is too dense with numbers and reporting without proper explanations of the results.
-
The evaluation does not tell whether HiLOT's accuracy comes from transport or whether the embedding is faithful to HOTT.
-
The evaluation does not tell whether HiLOT's accuracy comes from transport or whether the embedding is faithful to HOTT.
Questions for authors
n/a