Publications

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
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Kartik Ahuja
Ethan Caballero
Dinghuai Zhang
Jean-christophe Gagnon-audet
Yoshua Bengio
Ioannis Mitliagkas
Irina Rish
The invariance principle from causality is at the heart of notable approaches such as invariant risk minimization (IRM) that seek to address… (see more) out-of-distribution (OOD) generalization failures. Despite the promising theory, invariance principle-based approaches fail in common classification tasks, where invariant (causal) features capture all the information about the label. Are these failures due to the methods failing to capture the invariance? Or is the invariance principle itself insufficient? To answer these questions, we revisit the fundamental assumptions in linear regression tasks, where invariance-based approaches were shown to provably generalize OOD. In contrast to the linear regression tasks, we show that for linear classification tasks we need much stronger restrictions on the distribution shifts, or otherwise OOD generalization is impossible. Furthermore, even with appropriate restrictions on distribution shifts in place, we show that the invariance principle alone is insufficient. We prove that a form of the information bottleneck constraint along with invariance helps address key failures when invariant features capture all the information about the label and also retains the existing success when they do not. We propose an approach that incorporates both of these principles and demonstrate its effectiveness in several experiments.
2020-12-31
NeurIPS (published)
doi.org
openreview.net
Issue Link Label Recovery and Prediction for Open Source Software
Alexander Nicholson
Guo Jin L.C.
Jin L.C. Guo
Modern open source software development heavily relies on the issue tracking systems to manage their feature requests, bug reports, tasks, a… (see more)nd other similar artifacts. Together, those “issues” form a complex network with links to each other. The heterogeneous character of issues inherently results in varied link types and therefore poses a great challenge for users to create and maintain the label of the link manually. The goal of most existing automated issue link construction techniques ceases with only examining the existence of links between issues. In this work, we focus on the next important question of whether we can assess the type of issue link automatically through a data-driven method. We analyze the links between issues and their labels used the issue tracking system for 66 open source projects. Using three projects, we demonstrate promising results when using supervised machine learning classification for the task of link label recovery with careful model selection and tuning, achieving F1 scores of between 0.56-0.70 for the three studied projects. Further, the performance of our method for future link label prediction is convincing when there is sufficient historical data. Our work signifies the first step in systematically manage and maintain issue links faced in practice.
2020-12-31
2021 IEEE 29th International Requirements Engineering Conference Workshops (REW) (published)
doi.org
arxiv.org
Learning Neural Generative Dynamics for Molecular Conformation Generation
Minkai Xu
Shitong Luo
Yoshua Bengio
Jian Peng
Jian Tang
We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamic… (see more)s, sample conformations via computationally expensive simulations. Recently, machine learning methods have shown great potential by training on a large collection of conformation data. Challenges arise from the limited model capacity for capturing complex distributions of conformations and the difficulty in modeling long-range dependencies between atoms. Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph. We propose a method combining the advantages of both flow-based and energy-based models, enjoying: (1) a high model capacity to estimate the multimodal conformation distribution; (2) explicitly capturing the complex long-range dependencies between atoms in the observation space. Extensive experiments demonstrate the superior performance of the proposed method on several benchmarks, including conformation generation and distance modeling tasks, with a significant improvement over existing generative models for molecular conformation sampling.
2020-12-31
ICLR (published)
doi.org
openreview.net
Learning Robust State Abstractions for Hidden-Parameter Block MDPS
Amy Zhang
Shagun Sodhani
Khimya Khetarpal
Joelle Pineau
2020-12-31
ICLR (published)
openreview.net
openreview.net
Learning Task Decomposition with Ordered Memory Policy Network
Yuchen Lu
Yikang Shen
Siyuan Zhou
Aaron Courville
Joshua B. Tenenbaum
Chuang Gan
Many complex real-world tasks are composed of several levels of sub-tasks. Humans leverage these hierarchical structures to accelerate the l… (see more)earning process and achieve better generalization. In this work, we study the inductive bias and propose Ordered Memory Policy Network (OMPN) to discover subtask hierarchy by learning from demonstration. The discovered subtask hierarchy could be used to perform task decomposition, recovering the subtask boundaries in an unstruc-tured demonstration. Experiments on Craft and Dial demonstrate that our modelcan achieve higher task decomposition performance under both unsupervised and weakly supervised settings, comparing with strong baselines. OMPN can also bedirectly applied to partially observable environments and still achieve higher task decomposition performance. Our visualization further confirms that the subtask hierarchy can emerge in our model.
2020-12-31
ICLR (published)
doi.org
openreview.net
Learning a Universal Template for Few-shot Dataset Generalization
Eleni Triantafillou
Hugo Larochelle
Richard Zemel
Vincent Dumoulin
2020-12-31
ICML (published)
proceedings.mlr.press
proceedings.mlr.press
Learning with Gradient Descent and Weakly Convex Losses
Dominic Richards
Michael G. Rabbat
We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of … (see more)the empirical risk's Hessian is bounded in magnitude. By showing that this eigenvalue can control the stability of gradient descent, generalisation error bounds are proven that hold under a wider range of step sizes compared to previous work. Out of sample guarantees are then achieved by decomposing the test error into generalisation, optimisation and approximation errors, each of which can be bounded and traded off with respect to algorithmic parameters, sample size and magnitude of this eigenvalue. In the case of a two layer neural network, we demonstrate that the empirical risk can satisfy a notion of local weak convexity, specifically, the Hessian's smallest eigenvalue during training can be controlled by the normalisation of the layers, i.e., network scaling. This allows test error guarantees to then be achieved when the population risk minimiser satisfies a complexity assumption. By trading off the network complexity and scaling, insights are gained into the implicit bias of neural network scaling, which are further supported by experimental findings.
2020-12-31
AISTATS (published)
proceedings.mlr.press
proceedings.mlr.press