Search Results for author: Lexing Xie

Found 31 papers, 19 papers with code

Sampled Transformer for Point Sets

no code implementations28 Feb 2023 Shidi Li, Christian Walder, Alexander Soen, Lexing Xie, Miaomiao Liu

The sparse transformer can reduce the computational complexity of the self-attention layers to $O(n)$, whilst still being a universal approximator of continuous sequence-to-sequence functions.

Inductive Bias

Determinantal Point Process Likelihoods for Sequential Recommendation

1 code implementation25 Apr 2022 Yuli Liu, Christian Walder, Lexing Xie

Sequential recommendation is a popular task in academic research and close to real-world application scenarios, where the goal is to predict the next action(s) of the user based on his/her previous sequence of actions.

Sequential Recommendation

Fair Wrapping for Black-box Predictions

1 code implementation31 Jan 2022 Alexander Soen, Ibrahim Alabdulmohsin, Sanmi Koyejo, Yishay Mansour, Nyalleng Moorosi, Richard Nock, Ke Sun, Lexing Xie

We introduce a new family of techniques to post-process ("wrap") a black-box classifier in order to reduce its bias.


Factorized Fourier Neural Operators

1 code implementation27 Nov 2021 Alasdair Tran, Alexander Mathews, Lexing Xie, Cheng Soon Ong

We propose the Factorized Fourier Neural Operator (F-FNO), a learning-based approach for simulating partial differential equations (PDEs).

Interval-censored Hawkes processes

no code implementations16 Apr 2021 Marian-Andrei Rizoiu, Alexander Soen, Shidi Li, Pio Calderon, Leanne Dong, Aditya Krishna Menon, Lexing Xie

We propose the multi-impulse exogenous function - for when the exogenous events are observed as event time - and the latent homogeneous Poisson process exogenous function - for when the exogenous events are presented as interval-censored volumes.

Point Processes

Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series

1 code implementation15 Feb 2021 Alasdair Tran, Alexander Mathews, Cheng Soon Ong, Lexing Xie

We introduce Radflow, a novel model that embodies three key ideas: a recurrent neural network to obtain node embeddings that depend on time, the aggregation of the flow of influence from neighboring nodes with multi-head attention, and the multi-layer decomposition of time series.

Imputation Time Series +1

AttentionFlow: Visualising Influence in Networks of Time Series

no code implementations3 Feb 2021 Minjeong Shin, Alasdair Tran, Siqi Wu, Alexander Mathews, Rong Wang, Georgiana Lyall, Lexing Xie

The collective attention on online items such as web pages, search terms, and videos reflects trends that are of social, cultural, and economic interest.

Time Series Time Series Analysis

UNIPoint: Universally Approximating Point Processes Intensities

no code implementations28 Jul 2020 Alexander Soen, Alexander Mathews, Daniel Grixti-Cheng, Lexing Xie

The proof connects the well known Stone-Weierstrass Theorem for function approximation, the uniform density of non-negative continuous functions using a transfer functions, the formulation of the parameters of a piece-wise continuous functions as a dynamic system, and a recurrent neural network implementation for capturing the dynamics.

Open-Ended Question Answering Point Processes +1

Transform and Tell: Entity-Aware News Image Captioning

1 code implementation CVPR 2020 Alasdair Tran, Alexander Mathews, Lexing Xie

We address the first challenge by associating words in the caption with faces and objects in the image, via a multi-modal, multi-head attention mechanism.

Image Captioning Language Modelling +1

Variation across Scales: Measurement Fidelity under Twitter Data Sampling

1 code implementation21 Mar 2020 Siqi Wu, Marian-Andrei Rizoiu, Lexing Xie

This paper presents in-depth measurements on the effects of Twitter data sampling across different timescales and different subjects (entities, networks, and cascades).

Quantile Propagation for Wasserstein-Approximate Gaussian Processes

1 code implementation NeurIPS 2020 Rui Zhang, Christian J. Walder, Edwin V. Bonilla, Marian-Andrei Rizoiu, Lexing Xie

We show that QP matches quantile functions rather than moments as in EP and has the same mean update but a smaller variance update than EP, thereby alleviating EP's tendency to over-estimate posterior variances.

Bayesian Inference Gaussian Processes

Estimating Attention Flow in Online Video Networks

1 code implementation20 Aug 2019 Siqi Wu, Marian-Andrei Rizoiu, Lexing Xie

In this paper, we first construct the Vevo network -- a YouTube video network with 60, 740 music videos interconnected by the recommendation links, and we collect their associated viewing dynamics.

Navigate Recommendation Systems

ASNets: Deep Learning for Generalised Planning

1 code implementation4 Aug 2019 Sam Toyer, Felipe Trevizan, Sylvie Thiébaux, Lexing Xie

In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets).

Comparative Document Summarisation via Classification

1 code implementation6 Dec 2018 Umanga Bista, Alexander Mathews, Minjeong Shin, Aditya Krishna Menon, Lexing Xie

This paper considers extractive summarisation in a comparative setting: given two or more document groups (e. g., separated by publication time), the goal is to select a small number of documents that are representative of each group, and also maximally distinguishable from other groups.

Binary Classification Classification +2

Efficient Non-parametric Bayesian Hawkes Processes

1 code implementation8 Oct 2018 Rui Zhang, Christian Walder, Marian-Andrei Rizoiu, Lexing Xie

On two large-scale Twitter diffusion datasets, we show that our methods outperform the current state-of-the-art in goodness-of-fit and that the time complexity is linear in the size of the dataset.

SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text

1 code implementation CVPR 2018 Alexander Mathews, Lexing Xie, Xuming He

We develop a model that learns to generate visually relevant styled captions from a large corpus of styled text without aligned images.

Descriptive Image Captioning +1

Simplifying Sentences with Sequence to Sequence Models

no code implementations15 May 2018 Alexander Mathews, Lexing Xie, Xuming He

We simplify sentences with an attentive neural network sequence to sequence model, dubbed S4.

Style Transfer Text Generation +1

Modeling Popularity in Asynchronous Social Media Streams with Recurrent Neural Networks

no code implementations6 Apr 2018 Swapnil Mishra, Marian-Andrei Rizoiu, Lexing Xie

We find that results depend on the type of content being promoted: superusers are more successful in promoting Howto and Gaming videos, whereas the cohort of regular users are more influential for Activism videos.

#DebateNight: The Role and Influence of Socialbots on Twitter During the 1st 2016 U.S. Presidential Debate

2 code implementations27 Feb 2018 Marian-Andrei Rizoiu, Timothy Graham, Rui Zhang, Yifei Zhang, Robert Ackland, Lexing Xie

We collect a large dataset of tweets during the 1st U. S. Presidential Debate in 2016 (#DebateNight) and we analyze its 1. 5 million users from three perspectives: user influence, political behavior (partisanship and engagement) and botness.

Social and Information Networks

Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance

no code implementations17 Oct 2017 Aditya Mogadala, Umanga Bista, Lexing Xie, Achim Rettinger

Images in the wild encapsulate rich knowledge about varied abstract concepts and cannot be sufficiently described with models built only using image-caption pairs containing selected objects.

Action Schema Networks: Generalised Policies with Deep Learning

1 code implementation13 Sep 2017 Sam Toyer, Felipe Trevizan, Sylvie Thiébaux, Lexing Xie

In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems.

Beyond Views: Measuring and Predicting Engagement in Online Videos

1 code implementation8 Sep 2017 Siqi Wu, Marian-Andrei Rizoiu, Lexing Xie

The share of videos in the internet traffic has been growing, therefore understanding how videos capture attention on a global scale is also of growing importance.

Social and Information Networks Human-Computer Interaction

A Tutorial on Hawkes Processes for Events in Social Media

no code implementations21 Aug 2017 Marian-Andrei Rizoiu, Young Lee, Swapnil Mishra, Lexing Xie

This chapter provides an accessible introduction for point processes, and especially Hawkes processes, for modeling discrete, inter-dependent events over continuous time.

Point Processes

Revisiting revisits in trajectory recommendation

no code implementations17 Aug 2017 Aditya Krishna Menon, Dawei Chen, Lexing Xie, Cheng Soon Ong

Trajectory recommendation is the problem of recommending a sequence of places in a city for a tourist to visit.

Learning Points and Routes to Recommend Trajectories

1 code implementation25 Aug 2016 Dawei Chen, Cheng Soon Ong, Lexing Xie

Information about POIs are used to learn a POI ranking model that accounts for the start and end points of tours.

Probabilistic Knowledge Graph Construction: Compositional and Incremental Approaches

no code implementations21 Aug 2016 Dongwoo Kim, Lexing Xie, Cheng Soon Ong

Knowledge graph construction consists of two tasks: extracting information from external resources (knowledge population) and inferring missing information through a statistical analysis on the extracted information (knowledge completion).

graph construction

Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity

1 code implementation19 Feb 2016 Marian-Andrei Rizoiu, Lexing Xie, Scott Sanner, Manuel Cebrian, Honglin Yu, Pascal Van Hentenryck

Modeling and predicting the popularity of online content is a significant problem for the practice of information dissemination, advertising, and consumption.

Social and Information Networks

SentiCap: Generating Image Descriptions with Sentiments

no code implementations6 Oct 2015 Alexander Mathews, Lexing Xie, Xuming He

We design a system to describe an image with emotions, and present a model that automatically generates captions with positive or negative sentiments.

Decision Making Descriptive +2

Cannot find the paper you are looking for? You can Submit a new open access paper.