Sort by: Year Popularity Relevance

Understanding and mitigating gradient pathologies in physics-informed neural networks

, ,  - 2020

The widespread use of neural networks across different scientific domains often involves constraining them to satisfy certain symmetries, conservation laws, or other domain knowledge. Such constraints are often imposed as soft penalties during model training and effectively act as domain-specific regularizers of the empirical risk loss. Physics-i...


Predict your Click-out: Modeling User-Item Interactions and Session Actions in an Ensemble Learning Fashion

, , , ,  - 2020

This paper describes the solution of the POLINKS team to the RecSys Challenge 2019 that focuses on the task of predicting the last click-out in a session-based interaction. We propose an ensemble approach comprising a matrix factorization for modeling the interaction user-item, and a session-aware learning model implemented with a recurrent neura...


SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

, , , , , , ,  - 2020

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle to...


Adaptive Parameterization for Neural Dialogue Generation

, , , , ,  - 2020

Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic re...


Multi-Agent Interactions Modeling with Correlated Policies

, , , , , ,  - 2020

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we cast the multi-agent interactions modeling proble...


Analysis of Gender Inequality In Face Recognition Accuracy

, , , , ,  - 2020

We present a comprehensive analysis of how and why face recognition accuracy differs between men and women. We show that accuracy is lower for women due to the combination of (1) the impostor distribution for women having a skew toward higher similarity scores, and (2) the genuine distribution for women having a skew toward lower similarity score...


Regularizers for Single-step Adversarial Training

,  - 2020

The progress in the last decade has enabled machine learning models to achieve impressive performance across a wide range of tasks in Computer Vision. However, a plethora of works have demonstrated the susceptibility of these models to adversarial samples. Adversarial training procedure has been proposed to defend against such adversarial attacks...


Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization

, , ,  - 2020

Bayesian optimization (BO) is a popular approach to optimize expensive-to-evaluate black-box functions. A significant challenge in BO is to scale to high-dimensional parameter spaces while retaining sample efficiency. A solution considered in existing literature is to embed the high-dimensional space in a lower-dimensional manifold, often via a r...


Multi-organ Segmentation over Partially Labeled Datasets with Multi-scale Feature Abstraction

,  - 2020

This paper presents a unified training strategy that enables a novel multi-scale deep neural network to be trained on multiple partially labeled datasets for multi-organ segmentation. Multi-scale contextual information is effective for pixel-level label prediction, i.e. image segmentation. However, such important information is only partially exp...


Knowledge-aware Attention Network for Protein-Protein Interaction Extraction

, , , , ,  - 2020

Protein-protein interaction (PPI) extraction from published scientific literature provides additional support for precision medicine efforts. However, many of the current PPI extraction methods need extensive feature engineering and cannot make full use of the prior knowledge in knowledge bases (KB). KBs contain huge amounts of structured informa...