Related papers: Disentangling Learning Representations with Densit…
The (variational) graph auto-encoder is widely used to learn representations for graph-structured data. However, the formation of real-world graphs is a complicated and heterogeneous process influenced by latent factors. Existing encoders…
Disentangled representation learning has undoubtedly benefited from objective function surgery. However, a delicate balancing act of tuning is still required in order to trade off reconstruction fidelity versus disentanglement. Building on…
Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing…
A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…
Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have relied on learning…
In disentangled representation learning, the goal is to achieve a compact representation that consists of all interpretable generative factors in the observational data. Learning disentangled representations for graphs becomes increasingly…
Complex multivariate time series arise in many fields, ranging from computer vision to robotics or medicine. Often we are interested in the independent underlying factors that give rise to the high-dimensional data we are observing. While…
Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the…
We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the…
Recently, the disentangled latent space of a variational autoencoder (VAE) has been used to reason about multi-label out-of-distribution (OOD) test samples that are derived from different distributions than training samples. Disentangled…
Graph embedding (GE) methods embed nodes (and/or edges) in graph into a low-dimensional semantic space, and have shown its effectiveness in modeling multi-relational data. However, existing GE models are not practical in real-world…
Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…
We propose a novel VAE-based deep auto-encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all meaningful sources of variation and their cardinality. Our…
Variational autoencoders (VAEs) have recently been used for unsupervised disentanglement learning of complex density distributions. Numerous variants exist to encourage disentanglement in latent space while improving reconstruction.…
Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data. Learning such has been shown to require an inductive bias, which we explicitly encode in a generative model of images. Specifically,…
Disentangled representation learning offers useful properties such as dimension reduction and interpretability, which are essential to modern deep learning approaches. Although deep learning techniques have been widely applied to…
Fair representation learning aims to encode invariant representation with respect to the protected attribute, such as gender or age. In this paper, we design Fairness-aware Disentangling Variational AutoEncoder (FD-VAE) for fair…
Unsupervised disentangled representation learning from the unlabelled audio data, and high fidelity audio generation have become two linchpins in the machine learning research fields. However, the representation learned from an unsupervised…
We propose a new geometric method for measuring the quality of representations obtained from deep learning. Our approach, called Random Polytope Descriptor, provides an efficient description of data points based on the construction of…
Many real-world problems require reasoning across multiple scales, demanding models which operate not on single data points, but on entire distributions. We introduce generative distribution embeddings (GDE), a framework that lifts…