paper-with-me

홈 › Papers

Disentangled Interleaving Variational Encoding

2025-01-15 · Noelle Y. L. Wong, Eng Yeow Cheu, Zhonglin Chiam, Dipti Srinivasan

Conflicting objectives present a considerable challenge in interleaving multi-task learning, necessitating the need for meticulous design and balance to ensure effective learning of a representative latent data space across all tasks without mutual negative impact. Drawing inspiration from the concept of marginal and conditional probability distributions in probability theory, we design a principled and well-founded approach to disentangle the original input into marginal and conditional probability distributions in the latent space of a variational autoencoder. Our proposed model, Deep Disentangled Interleaving Variational Encoding (DeepDIVE) learns disentangled features from the original input to form clusters in the embedding space and unifies these features via the cross-attention mechanism in the fusion stage. We theoretically prove that combining the objectives for reconstruction and forecasting fully captures the lower bound and mathematically derive a loss function for disentanglement using Na\"ive Bayes. Under the assumption that the prior is a mixture of log-concave distributions, we also establish that the Kullback-Leibler divergence between the prior and the posterior is upper bounded by a function minimized by the minimizer of the cross entropy loss, informing our adoption of radial basis functions (RBF) and cross entropy with interleaving training for DeepDIVE to provide a justified basis for convergence. Experiments on two public datasets show that DeepDIVE disentangles the original input and yields forecast accuracies better than the original VAE and comparable to existing state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2501.08710

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementMulti-Task Learning

Similar Papers 제목 키워드 기반

Variational Tracking and Prediction with Generative Disentangled State-Space Models

2019-10-14 · Adnan Akhundov, Maximilian Soelch, Justin Bayer, Patrick van der Smagt

We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position in…

Bayesian InferencePositionState Space Models

Disentangled Representation Learning Using ($β$-)VAE and GAN

2022-08-09 · Mohammad Haghir EbrahimAbadi

Given a dataset of images containing different objects with different features such as shape, size, rotation, and x-y position; and a Variational Autoencoder (VAE); creating a disentangled encoding of these features in t…

DisentanglementGenerative Adversarial NetworkImage ReconstructionPosition+1

Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions

2021-08-14 · Andrea Burns, Aaron Sarna, Dilip Krishnan, Aaron Maschinot

Disentangled visual representations have largely been studied with generative models such as Variational AutoEncoders (VAEs). While prior work has focused on generative methods for disentangled representation learning, t…

Contrastive LearningDisentanglementRepresentation LearningSensitivity

Disentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders

2019-09-04 · NeurIPS Workshop DC_S1 2019 12 · Anonymous

A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a dis…

Disentanglement

Disentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders

2020-03-19 · Luis A. Pérez Rey

A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a dis…

Disentanglement