Publications

Domain Knowledge Discovery Guided by Software Trace Links

Jin L.C. Guo

Natawut Monaikul

Jane Cleland-Huang

Software-intensive projects are specified and modeled using domain terminology. Knowledge of the domain terminology is necessary for perform… (see more)ing many Software Engineering tasks such as impact analysis, compliance verification, and safety certification. However, discovering domain terminology and reasoning about their interrelationships for highly technical software and system engineering domains is a complex task which requires significant domain expertise and human effort. In this paper, we present a novel approach for leveraging trace links in software intensive systems to guide the process of mining facts that contain domain knowledge. The trace links which drive our mining process, define relationships between artifacts such as regulations and requirements and enable a guided search through high-yield combinations of domain terms. Our proof-of-concept evaluation shows that our approach aids in the discovery of domain facts even in highly complex technical domains. These domain facts can provide support for a variety of Software Engineering activities. As a use case, we demonstrate how the mined facts can facilitate the task of project Q&A.

2018-08-20

2018 5th International Workshop on Artificial Intelligence for Requirements Engineering (AIRE) (published)

doi.org

arxiv.org

The Deconfounded Recommender: A Causal Inference Approach to Recommendation

Yixin Wang

Dawen Liang

Laurent Charlin

David Blei

The goal of a recommender system is to show its users items that they will like. In forming its prediction, the recommender system tries to … (see more)answer: "what would the rating be if we 'forced' the user to watch the movie?" This is a question about an intervention in the world, a causal question, and so traditional recommender systems are doing causal inference from observational data. This paper develops a causal inference approach to recommendation. Traditional recommenders are likely biased by unobserved confounders, variables that affect both the "treatment assignments" (which movies the users watch) and the "outcomes" (how they rate them). We develop the deconfounded recommender, a strategy to leverage classical recommendation models for causal predictions. The deconfounded recommender uses Poisson factorization on which movies users watched to infer latent confounders in the data; it then augments common recommendation models to correct for potential confounding bias. The deconfounded recommender improves recommendation and it enjoys stable performance against interventions on test sets.

2018-08-19

ArXiv (preprint)

arxiv.org

Generalization of Equilibrium Propagation to Vector Field Dynamics

The biological plausibility of the backpropagation algorithm has long been doubted by neuroscientists. Two major reasons are that neurons wo… (see more)uld need to send two different types of signal in the forward and backward phases, and that pairs of neurons would need to communicate through symmetric bidirectional connections. We present a simple two-phase learning procedure for fixed point recurrent networks that addresses both these issues. In our model, neurons perform leaky integration and synaptic weights are updated through a local mechanism. Our learning method generalizes Equilibrium Propagation to vector field dynamics, relaxing the requirement of an energy function. As a consequence of this generalization, the algorithm does not compute the true gradient of the objective function, but rather approximates it at a precision which is proven to be directly related to the degree of symmetry of the feedforward and feedback weights. We show experimentally that our algorithm optimizes the objective function.

2018-08-13

ArXiv (preprint)

arxiv.org

Relevance learning via inhibitory plasticity and its implications for schizophrenia

Nathan Insel

Jordan Guerguiev

Blake Aaron Richards

Symptoms of schizophrenia may arise from a failure of cortical circuits to filter-out irrelevant inputs. Schizophrenia has also been linked … (see more)to disruptions to cortical inhibitory interneurons, consistent with the possibility that in the normally functioning brain, these cells are in some part responsible for determining which inputs are relevant and which irrelevant. Here, we develop an abstract but biologically plausible neural network model that demonstrates how the cortex may learn to ignore irrelevant inputs through plasticity processes affecting inhibition. The model is based on the proposal that the amount of excitatory output from a cortical circuit encodes expected magnitude of reward or punishment (”relevance”), which can be trained using a temporal difference learning mechanism acting on feed-forward inputs to inhibitory interneurons. The model exhibits learned irrelevance and blocking, which become impaired following disruptions to inhibitory units. When excitatory units are connected to a competitive-learning output layer, the relevance code is capable of modulating learning and activity. Accordingly, the combined network is capable of recapitulating published experimental data linking inhibition in frontal cortex with fear learning and expression. Finally, the model demonstrates how relevance learning can take place in parallel with other types of learning, through plasticity rules involving inhibitory and excitatory components respectively. Altogether, this work offers a theory of how the cortex learns to selectively inhibit inputs, providing insight into how relevance-assignment problems may emerge in schizophrenia.

2018-07-31

PLoS Comput. Biol. (published)

doi.org

Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information

Eric Larsen

Andrea Lodi

2018-07-30

arXiv.org (preprint)

doi.org

arxiv.org

Attend Before you Act: Leveraging human visual attention for continual learning

Khimya Khetarpal

Doina Precup

When humans perform a task, such as playing a game, they selectively pay attention to certain parts of the visual input, gathering relevant … (see more)information and sequentially combining it to build a representation from the sensory data. In this work, we explore leveraging where humans look in an image as an implicit indication of what is salient for decision making. We build on top of the UNREAL architecture in DeepMind Lab's 3D navigation maze environment. We train the agent both with original images and foveated images, which were generated by overlaying the original images with saliency maps generated using a real-time spectral residual technique. We investigate the effectiveness of this approach in transfer learning by measuring performance in the context of noise in the environment.

2018-07-24

ArXiv (preprint)

arxiv.org

Active Search of Connections for Case Building and Combating Human Trafficking

Reihaneh Rabbany

David Bayani

Artur Dubrawski

How can we help an investigator to efficiently connect the dots and uncover the network of individuals involved in a criminal activity based… (see more) on the evidence of their connections, such as visiting the same address, or transacting with the same bank account? We formulate this problem as Active Search of Connections, which finds target entities that share evidence of different types with a given lead, where their relevance to the case is queried interactively from the investigator. We present RedThread, an efficient solution for inferring related and relevant nodes while incorporating the user's feedback to guide the inference. Our experiments focus on case building for combating human trafficking, where the investigator follows leads to expose organized activities, i.e. different escort advertisements that are connected and possibly orchestrated. RedThread is a local algorithm and enables online case building when mining millions of ads posted in one of the largest classified advertising websites. The results of RedThread are interpretable, as they explain how the results are connected to the initial lead. We experimentally show that RedThread learns the importance of the different types and different pieces of evidence, while the former could be transferred between cases.

2018-07-18

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (published)

doi.org

Undersampling and Bagging of Decision Trees in the Analysis of Cardiorespiratory Behavior for the Prediction of Extubation Readiness in Extremely Preterm Infants

Lara Kanbar

Charles Onu

Wissam Shalish

Karen A. Brown

Guilherme M. Sant’Anna

Robert E. Kearney

Doina Precup

Extremely preterm infants often require endotracheal intubation and mechanical ventilation during the first days of life. Due to the detrime… (see more)ntal effects of prolonged invasive mechanical ventilation (IMV), clinicians aim to extubate infants as soon as they deem them ready.Unfortunately, existing strategies for prediction of extubation readiness vary across clinicians and institutions, and lead to high reintubation rates. We present an approach using Random Forest classifiers for the analysis of cardiorespiratory variability to predict extubation readiness. We address the issue of data imbalance by employing random undersampling of examples from the majority class before training each Decision Tree in a bag. By incorporating clinical domain knowledge, we further demonstrate that our classifier could have identified 71% of infants who failed extubation, while maintaining a success detection rate of 78%.

2018-07-17

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (published)

doi.org

arxiv.org

Eligibility Traces for Options

Ayush Jain

Doina Precup

Temporally extended actions not only represent knowledge in the hierarchical setup in reinforcement learning, they also improve exploration … (see more)while reducing the complexity of choosing actions. The option framework provides a concrete way to implement and reason about temporal abstraction. This work attempts to test the utility of eligibility traces with options and find good ways of doing multi-step intra-option updates. Three algorithms, based on off-policy methods - importance sampling, tree-backup and retrace, are proposed for using eligibility traces with options.

2018-07-08

International Joint Conference on Autonomous Agents and Multiagent Systems (published)

doi.org

Feature-wise transformations

Harm Vries

2018-07-08

Distill (published)

doi.org

MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation

Konstantinos Drossos

Stylianos Ioannis Mimilakis

Dmitriy Serdyuk

Gerald Schuller

Tuomas Virtanen

Yoshua Bengio

Monaural singing voice separation task focuses on the prediction of the singing voice from a single channel music mixture signal. Current st… (see more)ate of the art (SOTA) results in monaural singing voice separation are obtained with deep learning based methods. In this work we present a novel recurrent neural approach that learns long-term temporal patterns and structures of a musical piece. We build upon the recently proposed Masker-Denoiser (MaD) architecture and we enhance it with the Twin Networks, a technique to regularize a recurrent generative network using a backward running copy of the network. We evaluate our method using the Demixing Secret Dataset and we obtain an increment to signal-to-distortion ratio (SDR) of 0.37 dB and to signal-to-interference ratio (SIR) of 0.23 dB, compared to previous SOTA results.

2018-07-07

2018 International Joint Conference on Neural Networks (IJCNN) (published)

doi.org

arxiv.org

Information Fusion in Deep Convolutional Neural Networks for Biomedical Image Segmentation 1

Mohammad Havaei

Nicolas Guizard

Nicolas Chapados

Yoshua Bengio

2018-07-03

Signal Processing and Machine Learning for Biomedical Big Data (published)

doi.org