- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This work proposes a new VFL model called X-VFL which handles non-aligned data with missing features and supports locally independent inference.
Critical strengths
This work proposes a new VFL architecture to handle non-aligned data with missing features in VFL. Theoretical analysis on convergence and experimental results on performance are provided to validate the model.
Critical weaknesses
The demonstrated scope is narrow and a comparison study with the SOTA models is not included. There are some concerns on on the proposed model, for instance, and as explained in questions.
Questions for authors
-
There are three missing mechanisms in general [1], missing completely at random, missing at random, and missing not at random for the training and test datasets. Not all of these scenarios are considered in this work, so the model and its evaluation are limited. Moreover, the proposed model is applied to labeled datasets and no explanation is provided on how to extend it to unlabeled data, while recent works on VFL consider unlabeled as well as labeled datasets. [1] Roderick JA Little and Donald B Rubin. Statistical analysis with missing data, volume 793. John Wiley & Sons, 2019.
-
The comparison study is limited. For instance, it is necessary to compare the proposed model with the following two recent models: [2] Yuanqin He, Yan Kang, Xinyuan Zhao, Jiahuan Luo, Lixin Fan, Yuxing Han, and Qiang Yang. A hybrid self-supervised learning framework for vertical federated learning. IEEE Transactions on Big Data, 2024. [3] K. Hong et. al, Deep Latent Variable Model Based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios, In International Conference on Learning Representation 2026.
-
In the two client setting, is computed from client B and the components of for missing features are adopted to obtain . So, the resulting seems to be more dependent on from the other client B than the client A's features. Moreover, the average is the input for the function , meaning that the output from is more dependent on client B and the features of client A seem to affect the output of relatively less. Since the existing features of client A are important information, does the proposed method make sense from this perspective? Do we need to consider a weighted average instead of the equal-weight average? The features of some clients may be more important than those of the other clients.
-
In (3) both and are used, but is generated with the completed features . Recall that is obtained by adopting from the output of XCom_a for the missing features in the data. If is possible or all features of client A exist, then has no adoptation from XCom and both are the same. In this case, is it meaningful to consider both and ? If the reviewer misunderstands this, a detailed explanation would be helpful.
-
In (3) and are used as the inputs of the similarity loss function, but it is also possible to consider and as the inputs of the same similarity loss function. Obviously, we can train XCom in the latter case.