Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts

• URL: http://arxiv.org/abs/2410.08245v2
• Date: Thu, 31 Oct 2024 10:44:50 GMT
• Title: Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts
• Authors: Sukwon Yun, Inyoung Choi, Jie Peng, Yangfan Wu, Jingxuan Bao, Qiyiwen Zhang, Jiayi Xin, Qi Long, Tianlong Chen,
• Abstract summary: We propose Flex-MoE, a new framework designed to flexibly incorporate arbitrary modality combinations. We evaluate Flex-MoE on the ADNI dataset, which encompasses four modalities in the Alzheimer's Disease domain, as well as on the MIMIC-IV dataset.
• Score: 31.395361664653677
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal learning has gained increasing importance across various fields, offering the ability to integrate data from diverse sources such as images, text, and personalized records, which are frequently observed in medical domains. However, in scenarios where some modalities are missing, many existing frameworks struggle to accommodate arbitrary modality combinations, often relying heavily on a single modality or complete data. This oversight of potential modality combinations limits their applicability in real-world situations. To address this challenge, we propose Flex-MoE (Flexible Mixture-of-Experts), a new framework designed to flexibly incorporate arbitrary modality combinations while maintaining robustness to missing data. The core idea of Flex-MoE is to first address missing modalities using a new missing modality bank that integrates observed modality combinations with the corresponding missing ones. This is followed by a uniquely designed Sparse MoE framework. Specifically, Flex-MoE first trains experts using samples with all modalities to inject generalized knowledge through the generalized router ($\mathcal{G}$-Router). The $\mathcal{S}$-Router then specializes in handling fewer modality combinations by assigning the top-1 gate to the expert corresponding to the observed modality combination. We evaluate Flex-MoE on the ADNI dataset, which encompasses four modalities in the Alzheimer's Disease domain, as well as on the MIMIC-IV dataset. The results demonstrate the effectiveness of Flex-MoE highlighting its ability to model arbitrary modality combinations in diverse missing modality scenarios. Code is available at https://github.com/UNITES-Lab/flex-moe.

Related papers

• I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts [33.97906750476949]
  We propose I2MoE (Interpretable Multimodal Interaction-aware Mixture of Experts) to enhance modality fusion.<n>I2MoE explicitly modeling diverse multimodal interactions, as well as providing interpretation on a local and global level.<n>I2MoE is flexible enough to be combined with different fusion techniques, consistently improves task performance, and provides interpretation across various real-world scenarios.
  arXiv  Detail & Related papers  (2025-05-25T15:34:29Z)
• SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection [73.49799596304418]
  This paper introduces a new task called Multi-Modal datasets and Multi-Task Object Detection (M2Det) for remote sensing. It is designed to accurately detect horizontal or oriented objects from any sensor modality. This task poses challenges due to 1) the trade-offs involved in managing multi-modal modelling and 2) the complexities of multi-task optimization.
  arXiv  Detail & Related papers  (2024-12-30T02:47:51Z)
• MINIMA: Modality Invariant Image Matching [52.505282811925454]
  We present MINIMA, a unified image matching framework for multiple cross-modal cases. We scale up the modalities from cheap but rich RGB-only matching data, by means of generative models. With MD-syn, we can directly train any advanced matching pipeline on randomly selected modality pairs to obtain cross-modal ability.
  arXiv  Detail & Related papers  (2024-12-27T02:39:50Z)
• FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts [4.412721048192925]
  We present FedMoE, the efficient personalized Federated Learning framework to address data heterogeneity. FedMoE is composed of two fine-tuning stages. In the first stage, FedMoE simplifies the problem by conducting a search based on observed activation patterns. In the second stage, these submodels are distributed to clients for further training and returned for server aggregating.
  arXiv  Detail & Related papers  (2024-08-21T03:16:12Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• All in One Framework for Multimodal Re-identification in the Wild [58.380708329455466]
  multimodal learning paradigm for ReID introduced, referred to as All-in-One (AIO) AIO harnesses a frozen pre-trained big model as an encoder, enabling effective multimodal retrieval without additional fine-tuning. Experiments on cross-modal and multimodal ReID reveal that AIO not only adeptly handles various modal data but also excels in challenging contexts.
  arXiv  Detail & Related papers  (2024-05-08T01:04:36Z)
• NativE: Multi-modal Knowledge Graph Completion in the Wild [51.80447197290866]
  We propose a comprehensive framework NativE to achieve MMKGC in the wild. NativE proposes a relation-guided dual adaptive fusion module that enables adaptive fusion for any modalities. We construct a new benchmark called WildKGC with five datasets to evaluate our method.
  arXiv  Detail & Related papers  (2024-03-28T03:04:00Z)
• BlendX: Complex Multi-Intent Detection with Blended Patterns [4.852816974803059]
  We present BlendX, a suite of refined datasets featuring more diverse patterns than their predecessors. For dataset construction, we utilize both rule-baseds and a generative tool -- OpenAI's ChatGPT -- which is augmented with a similarity-driven strategy for utterance selection. Experiments on BlendX reveal that state-of-the-art MID models struggle with the challenges posed by the new datasets.
  arXiv  Detail & Related papers  (2024-03-27T06:13:04Z)
• FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion [29.130355774088205]
  FuseMoE is a mixture-of-experts framework incorporated with an innovative gating function. Designed to integrate a diverse number of modalities, FuseMoE is effective in managing scenarios with missing modalities and irregularly sampled data trajectories.
  arXiv  Detail & Related papers  (2024-02-05T17:37:46Z)
• Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection [14.261582708240407]
  Multimodal Federated learning (FL) aims to enrich model training in FL settings where clients are collecting measurements across multiple modalities. Key challenges to multimodal FL remain unaddressed, particularly in heterogeneous network settings. We propose mmFedMC, a new FL methodology that can tackle the above-mentioned challenges in multimodal settings.
  arXiv  Detail & Related papers  (2024-01-30T02:16:19Z)
• FedMFS: Federated Multimodal Fusion Learning with Selective Modality Communication [11.254610576923204]
  We propose Federated Multimodal Fusion learning with Selective modality communication (FedMFS) Key idea is the introduction of a modality selection criterion for each device, which weighs (i) the impact of the modality, gauged by Shapley value analysis, against (ii) the modality model size as a gauge for communication overhead. Experiments on the real-world ActionSense dataset demonstrate the ability of FedMFS to achieve comparable accuracy to several baselines while reducing the communication overhead by over 4x.
  arXiv  Detail & Related papers  (2023-10-10T22:23:27Z)
• Learning Unseen Modality Interaction [54.23533023883659]
  Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a module that projects the multidimensional features of different modalities into a common space with rich information preserved.
  arXiv  Detail & Related papers  (2023-06-22T10:53:10Z)
• FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing [88.6654909354382]
  We present a pure transformer-based framework, dubbed the Flexible Modal Vision Transformer (FM-ViT) for face anti-spoofing. FM-ViT can flexibly target any single-modal (i.e., RGB) attack scenarios with the help of available multi-modal data. Experiments demonstrate that the single model trained based on FM-ViT can not only flexibly evaluate different modal samples, but also outperforms existing single-modal frameworks by a large margin.
  arXiv  Detail & Related papers  (2023-05-05T04:28:48Z)
• Flexible-Modal Face Anti-Spoofing: A Benchmark [66.18359076810549]
  Face anti-spoofing (FAS) plays a vital role in securing face recognition systems from presentation attacks. We establish the first flexible-modal FAS benchmark with the principle train one for all' We also investigate prevalent deep models and feature fusion strategies for flexible-modal FAS.
  arXiv  Detail & Related papers  (2022-02-16T16:55:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.