- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes CARE-KAN, a conflict-aware framework for robust multimodal sentiment analysis. It decomposes unimodal representations into consensus, orthogonal complement, and directional conflict components, and introduces a reliability-adaptive router to modulate their contributions. A zero-initialized residual gating mechanism incorporates the resulting evidence into a base multimodal representation, followed by a Kolmogorov–Arnold Network prediction head. Experiments on CMU-MOSI, CMU-MOSEI, CH-SIMS, and IEMOCAP report competitive clean performance and improved robustness under visual noise and acoustic dropout, supported by ablation studies and supplementary analyses.
Critical strengths
-
The paper addresses a meaningful problem by distinguishing potentially informative cross-modal disagreement from corruption-induced noise. The combination of structured evidence decomposition, reliability-adaptive routing, and gated residual fusion is reasonably motivated and provides a coherent framework for robust multimodal prediction.
-
The paper reports competitive results across four benchmarks and provide empirical support for the effectiveness of the overall architecture.
Critical weaknesses
-
In Eqs. (5)–(8), the estimated reliability scores attenuate the complement and conflict components within the CARE residual pathway. However, the original multimodal representation is always retained and directly added to the final representation, meaning that corrupted modality features can still influence the prediction through the base pathway. Moreover, the subsequent LayerNorm and KAN head make it difficult to infer the actual influence of a modality from its reliability weight alone. Although Figure 3(b) shows that visual reliability decreases under increasing noise, this does not directly demonstrate that the final prediction becomes less dependent on corrupted visual information. Similarly, the theoretical result in Eq. (9) only establishes a limiting initialization property of the residual pathway, rather than guaranteeing the absence of negative transfer after training. I would like to see more direct analyses of how the estimated reliability affects the final prediction, such as modality intervention or prediction-sensitivity experiments under controlled corruption.
-
The experimental evidence does not sufficiently validate the paper's central distinction between informative emotional conflict and corruption-induced disagreement. A major motivation of CARE-KAN is to preserve meaningful cross-modal disagreement while suppressing harmful sensory noise. However, the robustness evaluations in Section 4.3 primarily consider visual Gaussian noise and acoustic frame dropout, while Figure 3(a) relates the proposed conflict magnitude to prediction difficulty without independently establishing whether the disagreement is semantically informative. Consequently, the results support robustness to selected sensory corruptions but do not directly demonstrate the claimed ability to distinguish genuine affective conflict from noise. In addition, the comparisons omit recent relevant reliability-aware methods such as P-RMF (ACL 2025) [1], TF-Mamba (EMNLP 2025) [2], and EBMC (CVPR 2026) [3], which are closely related to the paper's reliability estimation and robust fusion objectives. More targeted conflict evaluations and comparisons under matched protocols would strengthen the central empirical claims.
Refs:
[1] Aoqiang Zhu et al. Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data. ACL 2025.
[2] Xiang Li et al. TF-Mamba: Text-enhanced Fusion Mamba with Missing Modalities for Robust Multimodal Sentiment Analysis. EMNLP 2025 Findings.
[3] Kang He et al. Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis. CVPR 2026.
[4] Yitong Zhu et al. QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis. ACL 2026.
Questions for authors
-
Since always retains all modality representations, how does the proposed reliability-aware routing mechanism prevent corrupted information from influencing the final prediction through the base pathway? Is there evidence that lowering a modality's reliability score actually reduces the final prediction's sensitivity to that modality?
-
How does CARE-KAN distinguish semantically meaningful cross-modal conflict from noise-induced divergence? In particular, does the proposed conflict representation capture useful affective disagreement independently of general sample difficulty or corruption severity?
-
The Zero-Gating analysis in Eq. (9) establishes a limiting property at initialization. What evidence supports the stronger claim that the gating mechanism prevents negative transfer after training? How does its performance compare with simpler residual scaling or conventional gated fusion under comparable conditions?
-
I would like to see evaluations on independently identified affective conflicts, such as sarcasm or deliberately incongruent emotional expressions, alongside corrupted inputs. Such experiments could more directly assess whether CARE-KAN preserves informative disagreement while suppressing irrelevant noise.
I would be willing to raise my score if the authors can adequately address these concerns, particularly through more direct validation of conflict-aware routing.
6 comments
Response to Q2. Does the conflict representation capture useful disagreement beyond difficulty or corruption?
The router uses consensus, complement, and conflict jointly; conflict magnitude alone is not defined as unreliability. To test predictive utility independently of model-defined conflict scores, we use CH-SIMS's human unimodal sentiment labels to identify 61 natural-conflict examples. All predictions are evaluated against the overall multimodal sentiment label. No-Conflict removes d_m while retaining consensus and complement; Raw Difference replaces the structured conflict representation. Noisy inputs use visual σ=0.5; classification metrics are percentages.
| Variant | Clean MAE ↓ | Clean F1 ↑ | Clean Acc-3 ↑ | Noisy MAE ↓ |
|---|---|---|---|---|
| DecAlign | 0.504 | 78.1 | 81.1 | 0.595 |
| No-Conflict | 0.465 | 80.1 | 83.6 | 0.528 |
| Raw Difference | 0.472 | 79.5 | 83.2 | 0.552 |
| Full CARE-KAN | 0.436 | 82.5 | 85.2 | 0.482 |
On the same conflict examples, Full improves clean/noisy MAE over No-Conflict by 0.029/0.046 and also outperforms raw differences. Thus, the stream provides predictive utility on annotation-defined incongruity, including clean inputs where no synthetic corruption is introduced. Because d_m is derived from joint features, this is a representation benefit, not a claim of newly created or statistically independent information.
We separately examine the difficulty confound on MOSI. Difficulty tiers use Base prediction error; low/high conflict groups use the learned conflict norm. ΔMAE is CARE-KAN minus Base.
| Difficulty | Conflict group | N | Base MAE | CARE-KAN MAE | ΔMAE ↓ |
|---|---|---|---|---|---|
| Easy | Low | 175 | 0.312 | 0.310 | −0.002 |
| Easy | High | 54 | 0.346 | 0.332 | −0.014 |
| Medium | Low | 145 | 0.665 | 0.655 | −0.010 |
| Medium | High | 83 | 0.720 | 0.648 | −0.072 |
| Hard | Low | 88 | 1.155 | 1.132 | −0.023 |
| Hard | High | 141 | 1.242 | 1.068 | −0.174 |
| Overall | All | 686 | 0.7380 | 0.6868 | −0.0512 |
High-conflict groups show larger improvements within each tier, particularly medium/hard examples. However, their baseline errors also remain higher within each tier. We explicitly acknowledge this residual confounding: the diagnostic does not establish independence from every difficulty factor. The independently labelled evaluation above and the controlled corruption comparison under Q4 provide complementary evidence.
Response to Q3. What supports gating after training compared with simpler residual scaling or conventional gates?
Eq. (9) is an initialization-limit result for the task-loss gradient under bounded quantities. Our finite initialization gives α≈0.00474, not zero; neither auxiliary-loss gradients nor subsequent optimization are covered. We have removed the interpretation of this result as a guarantee against negative transfer after training.
We retrain matched MOSI controls, retaining C3D, RAER, KAN, and the same training protocol in all CARE variants. Learned gates have upper bound 0.1. The fixed scale κ=0.025 is validation-selected; the global gate is 0.1·sigmoid(b), initialized at b=−3. Base is trained separately, unlike the inference-time residual-off intervention in Q1.
| Gate setting | Clean MAE ↓ | MAE, visual σ=0.5 ↓ | MAE, visual σ=1.0 ↓ |
|---|---|---|---|
| Base, no residual | 0.7380 ± 0.0052 | 0.8360 ± 0.0071 | 0.9200 ± 0.0094 |
| Fixed κ=0.025 | 0.7185 ± 0.0045 | 0.7852 ± 0.0062 | 0.8421 ± 0.0081 |
| Learned global gate | 0.7062 ± 0.0041 | 0.7624 ± 0.0055 | 0.8115 ± 0.0075 |
| Sample gate, b₀=0 | 0.7015 ± 0.0048 | 0.7482 ± 0.0051 | 0.7894 ± 0.0068 |
| Full sample gate, b₀=−3 | 0.6868 ± 0.0031 | 0.7280 ± 0.0042 | 0.7628 ± 0.0051 |
Full improves clean MAE over fixed scaling, a global gate, and ordinary sample-gate initialization by 0.0317, 0.0194, and 0.0147, respectively, and has lower noisy MAE in all three comparisons. Training checkpoints also show a smaller initial residual-to-base norm ratio: 0.0058 versus 0.0682 at epoch 1. At epoch 50, the ratios are 0.0381 versus 0.0395, while validation MAE is 0.684 versus 0.704. This supports near-zero initialization followed by useful residual learning. The evidence concerns measured training behavior and final performance; residual norms do not establish gradient insulation or universal absence of negative transfer.
Response to Q1. Does lowering reliability reduce final-output sensitivity despite the retained base pathway?
Corrupted features remain in the base pathway, so a low internal reliability score alone is insufficient evidence. We therefore intervene in the same five trained MOSI checkpoints, without retraining, on all 686 test examples. We override visual reliability after the sigmoid, then recompute softmax weighting, residual assembly, LayerNorm, the gate, and KAN. Corruption and perturbation draws are matched across conditions. Each example receives five visual perturbations with RMS 0.01; S_v is the mean absolute prediction change divided by perturbation RMS. Overrides apply in both forward passes.
Adaptive routing reduces final-output sensitivity by approximately 80.8% relative to forced high reliability, while improving noisy MAE from 0.9352 to 0.7628. Disabling the residual worsens both sensitivity and noisy MAE. Fixed-zero reliability performs slightly better under strong noise, but worsens clean MAE to 0.7164, showing the cost of suppressing useful visual evidence.
We also sweep the forced reliability at a separate, fixed noise level, σ=0.5:
Lower reliability reduces both local sensitivity and MAE throughout this tested sweep. These are measurements of the complete prediction, including downstream normalization and KAN. They support reduced predictive influence, not complete modality isolation or algebraic cancellation: the base, softmax-weighted consensus, and cross-modal features can still depend on visual inputs even when r_v=0.