Hyunjik Kim

Preprints | Publications

I'm a third year PhD student in machine learning at the University of Oxford, supervised by Prof. Yee Whye Teh in the Machine Learning group at the Department of Statistics. I also spend two days a week at DeepMind as a research scientist.

My research interests fall under the topic of scalable probabilistic inference and interpretable machine learning. My current research interests lie in deep generative models and representation learning, especially in using deep generative models to learn disentangled factors of variation in the data. I am also interested in gradient based inference for generative models with discrete units, which ties in closely with interpretability. Previously, I have worked on scaling up inference for Gaussian processes, in particular on regression models for collaborative filtering that are motivated by a scalable approximation to a GP, as well as a method for scaling up the compositional kernel search used by the Automatic Statistician via variational sparse GP methods.

Previously, I studied Mathematics at the University of Cambridge, from which I obtained B.A. and M.Math. degrees. I spent a summer at Microsoft Research, Cambridge as a research intern, and worked on collaborative filtering. I spent last summer interning at DeepMind working on unsupervised learning of disentangled representations.

Curriculum Vitae

E-mail: hkim@stats.ox.ac.uk

Recent

Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects

Abstract: We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep generative model for videos of moving objects. It can reliably discover and track objects throughout the sequence of frames, and can also generate future frames conditioning on the current frame, thereby simulating expected motion of objects. This is achieved by explicitly encoding object presence, locations and appearances in the latent variables of the model. SQAIR retains all strengths of its predecessor, Attend, Infer, Repeat (AIR, Eslami et. al., 2016), including learning in an unsupervised manner, and addresses its shortcomings. We use a moving multi-MNIST dataset to show limitations of AIR in detecting overlapping or partially occluded objects, and show how SQAIR overcomes them by leveraging temporal consistency of objects. Finally, we also apply SQAIR to real-world pedestrian CCTV data, where it learns to reliably detect, track and generate walking pedestrians with no supervision.

Adam Kosiorek, Hyunjik Kim, Ingmar Posner, Yee Whye Teh
NIPS 2018. Spotlight.
pdf | bibtex

Publications

Disentangling by Factorising

Abstract: We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon β-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

Hyunjik Kim, Andriy Mnih
ICML 2018
pdf | bibtex
Learning Disentangled Representations: From Perception to Control Workshop, NIPS 2017. Spotlight Talk.
pdf
Scaling up the Automatic Statistician: Scalable Structure Discovery using Gaussian Processes

Abstract: Automating statistical modelling is a challenging problem in artificial intelligence. The Automatic Statistician takes a first step in this direction, by employing a kernel search algorithm with Gaussian Processes (GP) to provide interpretable statistical models for regression problems. However this does not scale due to its O(N^3) running time for the model selection. We propose Scalable Kernel Composition (SKC), a scalable kernel search algorithm that extends the Automatic Statistician to bigger data sets. In doing so, we derive a cheap upper bound on the GP marginal likelihood that sandwiches the marginal likelihood with the variational lower bound. We show that the upper bound is significantly tighter than the lower bound and thus useful for model selection.

Hyunjik Kim, Yee Whye Teh
AISTATS 2018. Oral.
pdf | bibtex
AutoML 2016, Journal of Machine Learning Research Workshop and Conference Proceedings.
Practical Bayesian Nonparametrics Workshop, NIPS 2016. Oral & Travel Award.
pdf

Preprints

Collaborative Filtering with Side Information: a Gaussian Process Perspective

Abstract: We tackle the problem of collaborative filtering (CF) with side information, through the lens of Gaussian Process (GP) regression. Driven by the idea of using the kernel to explicitly model user-item similarities, we formulate the GP in a way that allows the incorporation of low-rank matrix factorisation, arriving at our model, the Tucker Gaussian Process (TGP). Consequently, TGP generalises classical Bayesian matrix factorisation models, and goes beyond them to give a natural and elegant method for incorporating side information, giving enhanced predictive performance for CF problems. Moreover we show that it is a novel model for regression, especially well-suited to grid-structured data and problems where the dependence on covariates is close to being separable.

Hyunjik Kim, Xiaoyu Lu, Seth Flaxman, Yee Whye Teh
ArXiv, 2016
pdf | bibtex

Public Engagement


Introducing Machine Learning to the Public

I helped create a cute two-minute animation that introduces machine learning to the general public, along with friends at Oxford. Check it out below!



Further details can be found here