- Rating
- 3
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
To address the issue of update conflicts arising from direct aggregation of text adaptation parameters in federated vision-language learning—where different clients utilize different languages—the authors propose MERIDIAN. This framework balances knowledge sharing and client-specific personalization through language-cluster-specific shared text adapters, locally retained personalized language adapters, and a cross-language anchoring loss. The anchoring loss leverages category descriptions in English, Chinese, and Arabic to constrain image representations so that they correspond to the same category across different languages. While I believe this work offers an insightful approach to language-aware sharing, the experimental attribution, result consistency, and implementation details in the current manuscript require further refinement.
Critical strengths
-
The authors analyze the sources of heterogeneity in federated vision-language learning and complement existing research by incorporating perspectives centered on differences in categories and image domains.
-
The authors substantiate their arguments through comprehensive, multi-dimensional experiments, including comparisons with backbone baselines, component ablation studies, gradient analysis, evaluations on low-resource languages, and scalability tests regarding client size.
Critical weaknesses
-
The contribution of language grouping has not been fully validated; among the six default language clusters, four contain only a single client, meaning their "family adapters" effectively function as local parameters. The study lacks control conditions involving random grouping, data-driven grouping, or parameter-count matching.
-
The author's definitions regarding cross-lingual and low-resource evaluation lack clarity, and it is not specified how family/local adapters are utilized for the target training languages; furthermore, the evaluation is limited to merely changing the language of the class templates, failing to fully assess performance on realistic multilingual image-text tasks.
Questions for authors
-
How are the semantic router, bidirectional distillation, and other illustrated components implemented? If they are used, why does the full training objective not include corresponding terms for them?
-
Which set of parameters does the gradient conflict analysis target, and how are data discrepancies accounted for?
-
The author has been somewhat careless with the figures; I hope the author revises them, otherwise I will lower my rating.
5 comments
W2.
We agree that the evaluation terminology and scope require clearer definitions.
MERIDIAN is primarily evaluated in multilingual class-description-based vision-language classification. The original manuscript includes language-specific and low-resource evaluations (Table 7) and cross-language evaluations (Table 12).
We distinguish three settings:
- Training-language evaluation: evaluation on languages represented during federated adaptation.
- Cross-language template evaluation: evaluation using class descriptions expressed in different languages.
- Low-resource adaptation: evaluation with limited language-specific training examples.
These settings should not be conflated with unrestricted multilingual image-text understanding.
Regarding adapter utilization, globally shared vision and text adapters are aggregated across clients, family-specific text adapters are aggregated only within language families, and personalized adapters remain client-local. CLAL encourages alignment of multilingual class semantics through shared representations.
In the revised manuscript, we will explicitly specify the adapter pathway and language-specific parameters used in each evaluation setting, distinguishing previously trained languages from genuinely unseen target languages.
We also acknowledge that class-template-based evaluation does not constitute a comprehensive assessment of multilingual image-text retrieval or free-form language understanding. Accordingly, our claims are restricted to the evaluated multilingual classification setting.
Q1.
We thank the reviewer for identifying the insufficient correspondence between Figure 2 and the original mathematical formulation.
As also discussed in our response to Reviewer gPCX, the original Section 3 did not adequately explain several components illustrated in Figure 2, including the semantic router, shared bottleneck, semantic anchor bank, vision-to-text bridge, and bidirectional distillation pathways.
The vision-to-text bridge is defined as
mapping visual features into the shared semantic representation space.
The general and personalized representations are combined as
Here, is obtained without client-specific projection adaptation, whereas incorporates a client-local projection adapter. Their fusion balances shared cross-modal representation learning with personalization.
We will expand Section 3 and Appendix C to explicitly define the roles and implementation of the semantic router, shared bottleneck, semantic anchors, and distillation pathways. We will also revise the Figure 2 caption to establish direct correspondence between the illustrated components and their mathematical definitions.
Crucially, we agree that every independently optimized distillation term must appear in the complete training objective. We will ensure that the revised formulation distinguishes actual optimization losses from architectural operations that introduce no separate loss, thereby aligning the figure, equations, and implementation description.
Q2. We appreciate the request for greater methodological precision.
Our gradient analysis examines the compatibility of client updates in language-sensitive adaptation components. Original Figure 1 reports within-family gradient cosine similarities of approximately to , averaging , whereas some cross-family comparisons are negative, including for CJK–Arabic.
These observations motivate language-aware aggregation but do not establish that linguistic differences are the sole cause of gradient conflict. We therefore consider two complementary analyses from the original manuscript.
Data heterogeneity. Table 6 shows that MERIDIAN retains a 4.65-percentage-point improvement under the near-IID setting (). This suggests that its performance advantage is not limited to strongly heterogeneous client distributions.
Linguistic characteristics. Table 5 reports positive associations between performance improvements and morphological complexity (, ) and tokenization fertility (, ).
Together, these findings support the relevance of linguistic heterogeneity while avoiding the unsupported causal claim that language differences alone explain gradient interference.
To improve reproducibility, we will revise the manuscript to explicitly identify the gradient-bearing adapter parameter subset, client-pair construction, measurement stage, and cosine-similarity aggregation procedure. We will also clarify the distinction between gradient-conflict measurements and clustering-performance comparisons.
Q3.
We thank the reviewer for identifying the presentation inconsistencies and agree that architectural figures must accurately reflect the implemented method.
We have identified the unintended red vector artifact in Figure 2, unresolved table references, citation inconsistencies, and insufficient correspondence between architectural components and their mathematical descriptions.
We have uploaded a revised version of the manuscript containing a corrected Figure 2. Because figures cannot be embedded in OpenReview comments, we describe the revision here and refer the reviewer to the updated PDF.
The revised figure makes the following explicit:
- Complete component coverage. Every module referenced in Section 3 now appears with a matching label, including the semantic router, the semantic anchor bank , the vision-to-text bridge , the shared bottleneck , and the frozen projections and .
- Explicit distillation pathways. The two distillation terms are shown separately with their operative forms, for the V→T direction and a Wasserstein distance for the T→V direction, together with the CLAL block and its EN/ZH/AR pivot languages.
- Dual-pathway fork. The general and fused representations and are shown at the point of the convex combination, immediately before the cosine-similarity scoring head .
- Objective consistency. All five optimized terms — , , , , and — are drawn as explicit contributors to , so that the figure, the equations, and the implementation agree. Architectural operations that introduce no separate loss are no longer depicted in a way that could suggest an independent objective term.
- Federated parameter scope. A dedicated row distinguishes globally aggregated parameters (vision adapters, anchors, , projections), per-family aggregated text adapters across families, and parameters that never leave the client (router, personalized projection, personalized text adapter). A legend encodes frozen, aggregatable, and local-only components, along with residual connections and routing paths.
The unintended visual artifact has been removed, and the affected table references and citations have been corrected. We have also expanded the Figure 2 caption to associate each illustrated module with its defining equation, and we clarify the general, personalized, and fused representation pathways to ensure consistency between the architectural illustration, the optimization objective, and the implementation.
These corrections concern presentation and methodological clarity and do not alter any reported experimental result.
We thank the reviewer again for these constructive comments, which have helped us sharpen both the methodological description and the scope of our claims. We are happy to provide any further clarification during the discussion period.
We sincerely thank the reviewer for recognizing MERIDIAN's motivation and comprehensive experimental evaluation. We appreciate the constructive feedback regarding language-family grouping, cross-lingual evaluation, architectural consistency, gradient analysis, and presentation. We address each concern below.
W1.
We agree that four of the six language families in the original 10-client setting contain only one client. Consequently, their family-specific adapters function as local adapters, without within-family aggregation. Nevertheless, these clients continue to benefit from globally shared vision and text adapters and cross-lingual semantic alignment.
To examine whether linguistic grouping provides benefits beyond arbitrary clustering, we conducted additional comparisons.
Table: Effect of clustering strategy (H-Mean %).
MERIDIAN outperforms random clustering by 2.23 percentage points, gradient-based clustering by 1.03 points, and script-based clustering by 0.83 points. These results support the value of linguistically informed grouping rather than arbitrary client partitioning.
We further compared alternative adapter configurations under approximately matched trainable-parameter budgets.
Table: Adapter configuration comparison (H-Mean %).
MERIDIAN achieves the highest performance, suggesting that its improvements are not attributable solely to increased adaptation capacity.
Importantly, we do not interpret improvements in singleton families as direct evidence of within-family aggregation. These gains may also result from globally shared representations and CLAL. We will explicitly clarify this distinction in the revised manuscript.
The larger-client experiments (original Tables 13–14) provide complementary evidence. MERIDIAN achieves H-Mean improvements of 7.75, 8.52, and 10.70 percentage points for 10, 20, and 30 clients, respectively, relative to the corresponding reference baselines.
Together, these results support language-aware adaptation while acknowledging the limitations of singleton families.
Together, these results support language-aware adaptation while acknowledging the limitations of singleton families.