Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910208747372544 |
|---|---|
| author | Meng, Chunlei Feng, Pengbin Fu, Rong Lee, Hoi Leong Du, Xiaojing Kang, Zhaolu Zhang, Zeyu Zhou, Weilin Ouyang, Chun Gan, Zhongxue |
| author_facet | Meng, Chunlei Feng, Pengbin Fu, Rong Lee, Hoi Leong Du, Xiaojing Kang, Zhaolu Zhang, Zeyu Zhou, Weilin Ouyang, Chun Gan, Zhongxue |
| contents | Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose Group Cognition Learning (GCL), a governed collaboration paradigm that applies a two-stage protocol after modality-specific encoding. In Stage 1 (Selective Interaction), a Routing Agent proposes directed interaction routes, and an Auditing Agent assigns sample-wise gates to emphasize exchanges that yield positive marginal predictive gain while suppressing redundant coupling. In Stage 2 (Consensus Formation), a Public-Factor Agent maintains an explicit shared factor, and an Aggregation Agent produces the final prediction through contribution-aware weighting while keeping each modality representation as a specialization channel. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that GCL mitigates dominance and coupling, establishing state-of-the-art results across both regression and classification benchmarks. Analysis experiments further demonstrate the effectiveness of the design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00370 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration Meng, Chunlei Feng, Pengbin Fu, Rong Lee, Hoi Leong Du, Xiaojing Kang, Zhaolu Zhang, Zeyu Zhou, Weilin Ouyang, Chun Gan, Zhongxue Machine Learning Computers and Society Multimedia Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose Group Cognition Learning (GCL), a governed collaboration paradigm that applies a two-stage protocol after modality-specific encoding. In Stage 1 (Selective Interaction), a Routing Agent proposes directed interaction routes, and an Auditing Agent assigns sample-wise gates to emphasize exchanges that yield positive marginal predictive gain while suppressing redundant coupling. In Stage 2 (Consensus Formation), a Public-Factor Agent maintains an explicit shared factor, and an Aggregation Agent produces the final prediction through contribution-aware weighting while keeping each modality representation as a specialization channel. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that GCL mitigates dominance and coupling, establishing state-of-the-art results across both regression and classification benchmarks. Analysis experiments further demonstrate the effectiveness of the design. |
| title | Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration |
| topic | Machine Learning Computers and Society Multimedia |
| url | https://arxiv.org/abs/2605.00370 |