Best (Student) Machine Learning Paper AwardTitle: Reparameterized Sampling for Generative Adversarial Networks
Authors: Yifei Wang, Yisen Wang, Jiansheng Yang and Zhouchen Lin
Abstract: Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs). However, in practice, they typically have poor sample efficiency because of the independent proposal sampling from the generator. In this work, we propose REP-GAN, a novel sampling method that allows general dependent proposals by REParameterizing the Markov chains into the latent space of the generator. Theoretically, we show that our reparameterized proposal admits a closed-form Metropolis-Hastings acceptanceratio. Empirically, extensive experiments on synthetic and real datasets demonstrate that our REP-GAN largely improves the sample efficiency and obtains better sample quality simultaneously.
First Runner-up (Student) Machine Learning Paper AwardTitle: Continual Learning with Dual Regularizations
Authors: Xuejun Han and Yuhong Guo
Abstract: Continual learning (CL) has received a great amount of attention in recent years and a multitude of continual learning approachesarose. In this paper, we propose a continual learning approach with dual regularizations to alleviate the well-known issue of catastrophic forgetting in a challenging continual learning scenario – domain incremental learning. We reserve a buffer of past examples, dubbed memory set, toretain some information about previous tasks. The key idea is to regularize the learned representation space as well as the model outputs by utilizing the memory set based on interleaving the memory examples into the current training process. We verify our approach on four CL dataset benchmarks. Our experimental results demonstrate that the proposed approach is consistently superior to the compared methods on all benchmarks, especially in the case of small buffer size.
Best Applied Data Science Paper AwardTitle: Open Data Science to fight COVID-19: Winning the 500k XPRIZE Pandemic Response Challenge
Authors: Miguel Angel Lozano, Oscar Garibo, Eloy Piñol, Miguel Rebollo, Kristina Polotskaya, Miguel Angel Garcia-March, J. Alberto Conejero, Francisco Escolano and Nuria Oliver
Abstract: In this paper, we describe the deep learning-based COVID-19 cases predictor and the Pareto-optimal Non-Pharmaceutical Intervention (NPI) prescriptor developed by the winning team of the 500k XPRIZE Pandemic Response Challenge, a four-month global competition organizedby the XPRIZE Foundation. The competition aimed at developing data-driven AI models to predict COVID-19 infection rates and to prescribe NPI Plans that governments, business leaders and organizations could implement to minimize harm when reopening their economies. In addition to the validation performed by XPRIZE with real data, the winning models were validated in a real-world scenario thanks to an ongoing collaboration with the Valencian Government in Spain. We believe that this experience contributes to the necessary transition to more evidence-driven policy-making, particularly during a pandemic.
Best Student Data Mining Paper AwardTitle: Conditional Neural Relational Inference for Interacting Systems
Authors: Joao Candido Ramos, Lionel Blondé, Stéphane Armand and Alexandros Kalousis
Abstract: In this work, we want to learn to model the dynamics of similar yet distinct groups of interacting objects. These groups follow some common physical laws that exhibit specificities that are captured through some vectorial description. We develop a model that allows us to do conditional generation from any such group given its vectorial description. Unlike previous work on learning dynamical systems that can only do trajectory completion and require a part of the trajectory dynamics to be provided as input in generation time, we do generation using only the conditioning vector with no access to generation time’s trajectories. We evaluate our model in the setting of modeling human gait and, in particular pathological human gait.
Test of time AwardsTitle: Influence and Passivity in Social Media
Authors: Daniel M. Romero, Wojciech Galuba, Sitaram Asur and Bernardo A. Huberman
Abstract: The ever-increasing amount of information flowing through Social Media forces the members of these networks to compete for attention and influence by relying on other people to spread their message. A large study of information propagation within Twitter reveals that the majority of users act as passive information consumers and do not forward the content to the network. Therefore, in order for individuals to become influential they must not only obtain attention and thus be popular, but also overcome user passivity. We propose an algorithm that determines the influence and passivity of users based on their information forwarding activity. An evaluation performed with a 2.5 million user dataset shows that our influence measure is a good predictor of URL clicks, outperforming several other measures that do not explicitly take user passivity into account. We demonstrate that high popularity does not necessarily imply high influence and vice-versa.
Praise from the Awards Chairs: Following Google Scholar this is, by far, the most cited paper from ECMLPKDD in Athens, 2011. Since its appearance and until August 2021, the paper has been mentioned more than 940 times (scholar.google.com), received 114 citations (Springer) and inspired a shift from focus to influencers only towards perceiving the role of passive social media users. The paper proposes an algorithm to determine the influence and passivity of users based on their information forwarding activity and shows that high popularity does not necessarily imply high influence and vice-versa.