Welcome!

The Computational Media Lab at the ANU focus on computational problems for understanding online media and their interactions with and among humans. We develop core methods in machine learning and optimization, and use them to formulate and solve problems in multimedia undestanding and online behavior analysis.

You may be interested in sampling the recent blog posts below, look at our research summary, publications, all past posts, or navigate by categories and tags.
Problems: social media popularity privacy language vision citations
Methods: deep learning stochastic process visualization
Meta: researchdata datasci news group-activity

Inverting a Random Walk - Problem Settings Posted on Jan 3, 2017
We discuss three approaches for graph inversion from steady state distribution of random walks. This first post compares the problem settings.


posted by Lexing Xie

Markov chains and random walk on graphs are long-standing subjects in applied math and related disciplines. Given a markov chain / transition matrix / graph, properties of the random walk such as steady state distribution, mixing time are well-studied. Only in recent years, however, the inverse problem has started gaining interest – that is, given some measurements after random walk on a graph, infer some version of the graph. This blog post compares three related but different problem settings in recent literature from (Kumar15), (Mackay15) and (Xie13).

Read More

Wombeyan Caves and National Cherry Festival Posted on Dec 15, 2016
We explore Australian caves and cherries in the second half of 2016.


posted by Siqi Wu, with edits from Lexing Xie

Australia has great weather for the ourdoors, no matter it’s winter or summer – that’s what we did, and here’s photo proof.

Read More

Conference Talks in October and November 2016 Posted on Nov 15, 2016
We gave presentations at ACM CIKM and the D2D CRC Annual Conference.


posted by Minjeong Shin and Lexing Xie

Our work received some pulicity in the “fall” conference season internationally and in Australia.

Read More

Feature Driven and Point Process Approaches for Popularity Prediction Posted on Aug 31, 2016
We pbridge the gap between problem settings and approaches for predicting the size of a retweeting cascade.


posted by Swapnil Mishra


Predicting popularity as number of retweets a tweet will get is an important and difficult task. It’s unclear which approaches, settings and features works best. Our current CIKM ‘16 paper bridges this gap by comparing across feature driven and point process approaches under both regression and classification settings.

Read More

Learning Points and Routes to Recommend Trajectories Posted on Aug 31, 2016
We present a novel approach to jointly rank points-of-interest and plan routes


posted by Dawei Chen


The problem of recommending tours to travellers is an important and broadly studied area. We consider the task of recommending a sequence of points-of-interest (POI), that simultaneously uses information about POIs and routes.

Read More

Probabilistic Knowledge Graph Construction Posted on Aug 31, 2016
We propose a new probabilistic knowledge base factorisation that benefits from the path structure of existing knowledge.


posted by Dongwoo Kim

Relational knowledge graphs formalise our understanding about the world and help us reason and infer in a wide range of tasks. The construction of a knowledge graph is an active research area with many important and challenging research questions. Throughout this research, we address some important problems in the knowledge graph construction and propose novel statistical relational models to solve the problems.

Read More

Visualizing Citation Patterns of Computer Science Conferences Posted on Aug 18, 2016
We plot the citation behavior over time for different subfields in computer science, using data from microsoft academic graph.


posted by Lexing Xie

Read More

Expecting to be HIP Posted on Aug 16, 2016
This post outlines techniques for computing the expected event rate for Hawkes processes, or the so-called Hawkes Intensity Process (HIP).


posted by Lexing Xie


We give a brief overview to a new method for computing expected event rate in unit time for point processes. This is important for estimating interval-censored Hawkes processes – or when the volume of events, and not individual event times are known.

Read More

How Long Do Papers Survive in the Collective Academic Memory? Posted on Aug 16, 2016
We plot the citation survival rate of many computer science conferences, using data from microsoft academic graph.


posted by Lexing Xie

Read More

Where are Ideas Coming from, and Going to? - Measuring citation flow in academic communities Posted on Jul 16, 2016
We plot the incoming and outgoing citation flow of many computer science conferences, using data from microsoft academic graph.


citation summary - NIPS

Read More

Group Activity: Climbing Mt. Kosciuszko Posted on Apr 2, 2016
We climbed to the top of Australia -- Mt. Kosciuszko, braving strong gust and below-freezing windchill´╝ü


On the 2nd of April, group members climbed the top of Australia, Mt. Kosciuszko. Kosciuszko is the highest mountain in Australia a mountain with a height of 2,228 metres.

Read More

Recent updates

  • 2016-12 Andrei and Lexing are delighted that Expecting to be HIP is accepted into WWW 2017 in Perth.
  • 2016-12 Photos for group outings are posted, at National Cherry Festival and Wombeyan Caves.
  • 2016-10 Three CIKM papers posted, check them out!.
  • 2016-03 Lexing is elected as an IEEE CAS Distinguished Lecturer 2016-2017.
  • 2016-03 Andrei is featured at the March'16 Wikimedia Research Showcase for his WSDM paper on "Evolution of Privacy Loss". Well done!
  • Getting in touch!
    -- drop us a line if you are interested in knowing more about our work, collaborating, or joining us. Compelling stories gets read and responded promptly.