Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives

• URL: http://arxiv.org/abs/2309.00380v3
• Date: Tue, 24 Sep 2024 13:59:59 GMT
• Title: Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives
• Authors: Marcel Hirt, Domenico Campolo, Victoria Leong, Juan-Pablo Ortega,
• Abstract summary: Devising deep latent variable models for multi-modal data has been a long-standing theme in machine learning research. In this work, we consider a variational objective that can tightly approximate the data log-likelihood. We develop more flexible aggregation schemes that avoid the inductive biases in PoE or MoE approaches.
• Score: 5.549794481031468
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Devising deep latent variable models for multi-modal data has been a long-standing theme in machine learning research. Multi-modal Variational Autoencoders (VAEs) have been a popular generative model class that learns latent representations that jointly explain multiple modalities. Various objective functions for such models have been suggested, often motivated as lower bounds on the multi-modal data log-likelihood or from information-theoretic considerations. To encode latent variables from different modality subsets, Product-of-Experts (PoE) or Mixture-of-Experts (MoE) aggregation schemes have been routinely used and shown to yield different trade-offs, for instance, regarding their generative quality or consistency across multiple modalities. In this work, we consider a variational objective that can tightly approximate the data log-likelihood. We develop more flexible aggregation schemes that avoid the inductive biases in PoE or MoE approaches by combining encoded features from different modalities based on permutation-invariant neural networks. Our numerical experiments illustrate trade-offs for multi-modal variational objectives and various aggregation schemes. We show that our variational objective and more flexible aggregation models can become beneficial when one wants to approximate the true joint distribution over observed modalities and latent variables in identifiable models.

Related papers

• Learning Multimodal Latent Generative Models with Energy-Based Prior [3.6648642834198797]
  We propose a novel framework that integrates the latent generative model with the EBM. This approach results in a more expressive and informative prior, better-capturing of information across multiple modalities.
  arXiv  Detail & Related papers  (2024-09-30T01:38:26Z)
• U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation [63.31007867379312]
  We introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantics. We employ feature fusion at multiple scales to ensure the effective extraction and integration of both global and local features. Experimental results demonstrate that our approach achieves superior performance across multiple datasets.
  arXiv  Detail & Related papers  (2024-05-24T08:58:48Z)
• Disentangling shared and private latent factors in multimodal Variational Autoencoders [6.680930089714339]
  Multimodal Variational Autoencoders, such as MVAE and MMVAE, are a natural choice for inferring those underlying latent factors and separating shared variation from private. We demonstrate limitations of existing models, and propose a modification how to make them more robust to modality-specific variation. Our findings are supported by experiments on synthetic as well as various real-world multi-omics data sets.
  arXiv  Detail & Related papers  (2024-03-10T23:11:05Z)
• Model Composition for Multimodal Large Language Models [71.5729418523411]
  We propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model. Our basic implementation, NaiveMC, demonstrates the effectiveness of this paradigm by reusing modality encoders and merging LLM parameters.
  arXiv  Detail & Related papers  (2024-02-20T06:38:10Z)
• Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles [95.49699178874683]
  We propose DiffDiv, an ensemble diversification framework exploiting Diffusion Probabilistic Models (DPMs) We show that DPMs can generate images with novel feature combinations, even when trained on samples displaying correlated input features. We show that DPM-guided diversification is sufficient to remove dependence on shortcut cues, without a need for additional supervised signals.
  arXiv  Detail & Related papers  (2023-11-23T15:47:33Z)
• Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks [92.32670915472099]
  We propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs) We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.
  arXiv  Detail & Related papers  (2023-10-03T17:37:52Z)
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling [54.94763543386523]
  Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the ( aggregate) posterior to encourage statistical independence of the latent factors. We present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method. Then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables.
  arXiv  Detail & Related papers  (2020-10-25T18:51:15Z)
• Variational Dynamic Mixtures [18.730501689781214]
  We develop variational dynamic mixtures (VDM) to infer sequential latent variables. In an empirical study, we show that VDM outperforms competing approaches on highly multi-modal datasets.
  arXiv  Detail & Related papers  (2020-10-20T16:10:07Z)
• Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models [86.9292779620645]
  We develop a contrastive framework for generative model learning, allowing us to train the model not just by the commonality between modalities, but by the distinction between "related" and "unrelated" multimodal data. Under our proposed framework, the generative model can accurately identify related samples from unrelated ones, making it possible to make use of the plentiful unlabeled, unpaired multimodal data.
  arXiv  Detail & Related papers  (2020-07-02T15:08:11Z)

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.