Publications

Extendable and invertible manifold learning with geometry regularized autoencoders
Andrés F. Duque
Sacha Morin
Guy Wolf
Kevin Moon
A fundamental task in data exploration is to extract simplified low dimensional representations that capture intrinsic geometry in data, esp… (see more)ecially for faithfully visualizing data in two or three dimensions. Common approaches to this task use kernel methods for manifold learning. However, these methods typically only provide an embedding of fixed input data and cannot extend to new data points. Autoencoders have also recently become popular for representation learning. But while they naturally compute feature extractors that are both extendable to new data and invertible (i.e., reconstructing original features from latent representation), they have limited capabilities to follow global intrinsic geometry compared to kernel-based manifold learning. We present a new method for integrating both approaches by incorporating a geometric regularization term in the bottleneck of the autoencoder. Our regularization, based on the diffusion potential distances from the recently-proposed PHATE visualization method, encourages the learned latent representation to follow intrinsic data geometry, similar to manifold learning algorithms, while still enabling faithful extension to new data and reconstruction of data in the original feature space from latent coordinates. We compare our approach with leading kernel methods and autoencoder models for manifold learning to provide qualitative and quantitative evidence of our advantages in preserving intrinsic structure, out of sample extension, and reconstruction. Our method is easily implemented for big-data applications, whereas other methods are limited in this regard.
2020-12-31
IEEE International Conference on Big Data (unknown)
doi.org
arxiv.org
Finding Archetypal Spaces Using Neural Networks
David van Dijk
Daniel B. Burkhardt
Matthew Amodio
Alexander Tong
Guy Wolf
Smita Krishnaswamy
Archetypal analysis is a data decomposition method that describes each observation in a dataset as a convex combination of "pure types" or a… (see more)rchetypes. These archetypes represent extrema of a data space in which there is a trade-off between features, such as in biology where different combinations of traits provide optimal fitness for different environments. Existing methods for archetypal analysis work well when a linear relationship exists between the feature space and the archetypal space. However, such methods are not applicable to systems where the feature space is generated non-linearly from the combination of archetypes, such as in biological systems or image transformations. Here, we propose a reformulation of the problem such that the goal is to learn a non-linear transformation of the data into a latent archetypal space. To solve this problem, we introduce Archetypal Analysis network (AAnet), which is a deep neural network framework for learning and generating from a latent archetypal representation of data. We demonstrate state-of-the-art recovery of ground-truth archetypes in non-linear data domains, show AAnet can generate from data geometry rather than from data density, and use AAnet to identify biologically meaningful archetypes in single-cell gene expression data.
2020-12-31
IEEE International Conference on Big Data (unknown)
doi.org
arxiv.org
Finite time analysis of temporal difference learning with linear function approximation: the tail averaged case
Gandharv Patil
Prashanth L.A.
Doina Precup
In this paper, we study the finite-time behaviour of temporal difference (TD) learning algorithms when combined with tail-averaging, and pr… (see more)esent instance dependent bounds on the parameter error of the tail-averaged TD iterate. Our error bounds hold in expectation as well as with high probability, exhibit a sharper rate of decay for the initial error (bias), and are comparable with existing bounds in the literature.
2020-12-31
(published)
www.semanticscholar.org
Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification
Charles A. Kantor
Marta Skreta
Brice Rauby
Léonard Boussioux
Emmanuel Jehanno
Alexandra Luccioni
David Rolnick
Hugues Talbot
Fine-grained classification aims at distinguishing between items with similar global perception and patterns, but that differ by minute deta… (see more)ils. Our primary challenges come from both small inter-class variations and large intra-class variations. In this article, we propose to combine several innovations to improve fine-grained classification within the use-case of wildlife, which is of practical interest for experts. We utilize geo-spatiotemporal data to enrich the picture information and further improve the performance. We also investigate state-of-the-art methods for handling the imbalanced data issue.
2020-12-31
IJCAI Workshop on AI for Social Good (unknown)
doi.org
arxiv.org
HADE: Hierarchical Affective Dialog Encoder for Personality Recognition in Conversation
Nabiha Asghar
P. Poupart
Jesse Hoey
Xin Jiang
M. Bradley
P. J. Lang
Affective
Kyunghyun Cho
Bart Van Merriënboer
Caglar Gul-666
Dzmitry Bahdanau
Holger Fethi Bougares
Pierre Colombo
Wojciech Witon
Ashutosh Modi
J. Kennedy
Mubbasir Kapadia
J. Devlin
Ming-Wei Chang
Kenton Lee … (see 35 more)
Jennifer Golbeck
Cristina Robles
Xiaodong Gu
Kang Min
Yoo Jung-Woo
Iulian Serban
Alessandro Sordoni
Ryan Lowe
Laurent Charlin
Joelle Pineau
Aaron C. Courville
Alireza Souri
Shafigheh Hosseinpour
Amir Ma-822
Edward P Tighe
Jennifer C. Ureta
B. Andrei
Ashish Vaswani
Noam Shazeer
Niki Parmar
David I. Watson
Lee Anna
Clark. 1992
On
Thomas Wolf
Lysandre Debut
Julien Victor Sanh
Clement Chaumond
Anthony Delangue
Pier-339 Moi
Tim ric Cistac
Rémi Rault
Morgan Louf
Funtowicz
Julien Chaumond
2020-12-31
(published)
www.semanticscholar.org
Hierarchical Graph Neural Nets Can Capture Long-Range Interactions
Ladislav Rampasek
Guy Wolf
Graph neural networks (GNNs) based on message passing between neighboring nodes are known to be insufficient for capturing long-range intera… (see more)ctions in graphs. In this project we study hierarchical message passing models that leverage a multi-resolution representation of a given graph. This facilitates learning of features that span large receptive fields without loss of local information, an aspect not studied in preceding work on hierarchical GNNs. We introduce Hierarchical Graph Net (HGNet), which for any two connected nodes guarantees existence of message-passing paths of at most logarithmic length w.r.t. the input graph size. Yet, under mild assumptions, its internal hierarchy maintains asymptotic size equivalent to that of the input graph. We observe that our HGNet outperforms conventional stacking of GCN layers particularly in molecular property prediction benchmarks. Finally, we propose two benchmarking tasks designed to elucidate capability of GNNs to leverage long-range interactions in graphs.
2020-12-31
IEEE International Workshop on Machine Learning for Signal Processing (published)
doi.org
arxiv.org
Image Dehazing in Disproportionate Haze Distributions
Shih-Chia Huang
Da-Wei Jaw
Wenli Li
Zhihui Lu
Sy-Yen Kuo
Benjamin C. M. Fung
Bo-Hao Chen
Thanisa Numnonda
Haze removal techniques employed to increase the visibility level of an image play an important role in many vision-based systems. Several t… (see more)raditional dark channel prior-based methods have been proposed to remove haze formation and thereby enhance the robustness of these systems. However, when the captured images contain disproportionate haze distributions, these methods usually fail to attain effective restoration in the restored image. Specifically, disproportionate haze distribution in an image means that the background region possesses heavy haze density and the foreground region possesses little haze density. This phenomenon usually occurs in a hazy image with a deep depth of field. In response, a novel hybrid transmission map-based haze removal method that specifically targets this situation is proposed in this work to achieve clear visibility restoration and effective information maintenance. Experimental results via both qualitative and quantitative evaluations demonstrate that the proposed method is capable of performing with higher efficacy when compared with other state-of-the-art methods, in respect to both background regions and foreground regions of restored test images captured in real-world environments.
2020-12-31
IEEE Access (published)
doi.org
Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Offline RL
Bogdan Mazoure
Paul Mineiro
Pavithra Srinath
Reza Sharifi Sedeh
Doina Precup
Adith Swaminathan
We study session-based recommendation scenarios where we want to recommend items to users during sequential interactions to improve their lo… (see more)ng-term utility. Optimizing a long-term metric is challenging because the learning signal (whether the recommendations achieved their desired goals) is delayed and confounded by other user interactions with the system. Immediately measurable proxies such as clicks can lead to suboptimal recommendations due to misalignment with the long-term metric. Many works have applied episodic reinforcement learning (RL) techniques for session-based recommendation but these methods do not account for policy-induced drift in user intent across sessions. We develop a new batch RL algorithm called Short Horizon Policy Improvement (SHPI) that approximates policy-induced distribution shifts across sessions. By varying the horizon hyper-parameter in SHPI, we recover well-known policy improvement schemes in the RL literature. Empirical results on four recommendation tasks show that SHPI can outperform matrix factorization, offline bandits, and offline RL baselines. We also provide a stable and computationally efficient implementation using weighted regression oracles.
2020-12-31
arXiv.org (preprint)
dblp.uni-trier.de
Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
Joelle Pineau
Philippe Vincent-Lamarre
Koustuv Sinha
Vincent Larivière
Alina Beygelzimer
Florence d'Alché-Buc
Emily Fox
Hugo Larochelle
One of the challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility… (see more), that is obtaining similar results as presented in a paper or talk, using the same code and data (when available), is a necessary step to verify the reliability of research findings. Reproducibility is also an important step to promote open and accessible research, thereby allowing the scientific community to quickly integrate new findings and convert ideas to practice. Reproducibility also promotes the use of robust experimental workflows, which potentially reduce unintentional errors. In 2019, the Neural Information Processing Systems (NeurIPS) conference, the premier international conference for research in machine learning, introduced a reproducibility program, designed to improve the standards across the community for how we conduct, communicate, and evaluate machine learning research. The program contained three components: a code submission policy, a community-wide reproducibility challenge, and the inclusion of the Machine Learning Reproducibility checklist as part of the paper submission process. In this paper, we describe each of these components, how it was deployed, as well as what we were able to learn from this initiative.
2020-12-31
Journal of Machine Learning Research (published)
doi.org
arxiv.org
Incorporating dynamic flight network in SEIR to model mobility between populations
Xiaoye Ding
Shenyang Huang
Abby Leung
Reihaneh Rabbany
Current efforts of modelling COVID-19 are often based on the standard compartmental models such as SEIR and their variations. As pre-symptom… (see more)atic and asymptomatic cases can spread the disease between populations through travel, it is important to incorporate mobility between populations into the epidemiological modelling. In this work, we propose to modify the commonly-used SEIR model to account for the dynamic flight network, by estimating the imported cases based on the air traffic volume as well as the test positive rate at the source. This modification, called Flight-SEIR, can potentially enable 1). early detection of outbreaks due to imported pre-symptomatic and asymptomatic cases, 2). more accurate estimation of the reproduction number and 3). evaluation of the impact of travel restrictions and the implications of lifting these measures. The proposed Flight-SEIR is essential in navigating through this pandemic and the next ones, given how interconnected our world has become.
2020-12-31
Applied Network Science (published)
doi.org
arxiv.org
Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization
Meng Cao
Yue Dong
Jackie CK Cheung
State-of-the-art abstractive summarization systems often generate hallucinations ; i.e., content that is not directly inferable from the sou… (see more)rce text. Despite being assumed incorrect, many of the hallucinated contents are consistent with world knowledge (factual hallucinations). Including these factual hallucinations into a summary can be beneficial in providing additional background information. In this work, we propose a novel detection approach that separates factual from non-factual hallucinations of entities. Our method is based on an entity’s prior and posterior probabilities according to pre-trained and finetuned masked language models, respectively. Empirical re-sults suggest that our method vastly outperforms three strong baselines in both accuracy and F1 scores and has a strong correlation with human judgements on factuality classification tasks. Furthermore, our approach can provide insight into whether a particular hallucination is caused by the summarizer’s pre-training or fine-tuning step. 1
2020-12-31
arXiv.org (preprint)
dblp.uni-trier.de
Investigating Design Anti-pattern and Design Pattern Mutations and Their Change- and Fault-proneness
Zeinab Kermansaravi
Md Saidur Rahman
Foutse Khomh
Fehmi Jaafar
Yann-Gaël Guéhéneuc
During software evolution, inexperienced developers may introduce design anti-patterns when they modify their software systems to fix bugs o… (see more)r to add new functionalities based on changes in requirements. Developers may also use design patterns to promote software quality or as a possible cure for some design anti-patterns. Thus, design patterns and design anti-patterns are introduced, removed, and mutated from one another by developers. Many studies investigated the evolution of design patterns and design anti-patterns and their impact on software development. However, they investigated design patterns or design anti-patterns in isolation and did not consider their mutations and the impact of these mutations on software quality. Therefore, we report our study of bidirectional mutations between design patterns and design anti-patterns and the impacts of these mutations on software change- and fault-proneness. We analyzed snapshots of seven Java software systems with diverse sizes, evolution histories, and application domains. We built Markov models to capture the probability of occurrences of the different design patterns and design anti-patterns mutations. Results from our study show that (1) design patterns and design anti-patterns mutate into other design patterns and/or design anti-patterns. They also show that (2) some change types primarily trigger mutations of design patterns and design anti-patterns (renaming and changes to comments, declarations, and operators), and (3) some mutations of design anti-patterns and design patterns are more faulty in specific contexts. These results provide important insights into the evolution of design patterns and design anti-patterns and its impact on the change- and fault-proneness of software systems.
2020-12-31
Empirical Software Engineering (published)
doi.org
arxiv.org