Machine Learning

---

Factor Graph Attention (1904.05880v1)

Idan Schwartz, Seunghak Yu, Tamir Hazan, Alexander Schwing

2019-04-11

Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge. Attention mechanisms have demonstrated compelling results to extract details in visual question answering and also provide a convincing framework for visual dialog due to their interpretability and effectiveness. However, the many data utilities that accompany visual dialog challenge existing attention techniques. We address this issue and develop a general attention mechanism for visual dialog which operates on any number of data utilities. To this end, we design a factor graph based attention mechanism which combines any number of utility representations. We illustrate the applicability of the proposed approach on the challenging and recently introduced VisDial datasets, outperforming recent state-of-the-art methods by 1.1% for VisDial0.9 and by 2% for VisDial1.0 on MRR. Our ensemble model improved the MRR score on VisDial1.0 by more than 6%.

Max-Sliced Wasserstein Distance and its use for GANs (1904.05877v1)

Ishan Deshpande, Yuan-Ting Hu, Ruoyu Sun, Ayis Pyrros, Nasir Siddiqui, Sanmi Koyejo, Zhizhen Zhao, David Forsyth, Alexander Schwing

2019-04-11

Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities, showing promise for dataset augmentation, image-to-image translation and feature learning. However, to model high-dimensional distributions, sequential training and stacked architectures are common, increasing the number of tunable hyper-parameters as well as the training time. Nonetheless, the sample complexity of the distance metrics remains one of the factors affecting GAN training. We first show that the recently proposed sliced Wasserstein distance has compelling sample complexity properties when compared to the Wasserstein distance. To further improve the sliced Wasserstein distance we then analyze its `projection complexity' and develop the max-sliced Wasserstein distance which enjoys compelling sample complexity while reducing projection complexity, albeit necessitating a max estimation. We finally illustrate that the proposed distance trains GANs on high-dimensional images up to a resolution of 256x256 easily.

Knowledge Flow: Improve Upon Your Teachers (1904.05878v1)

Iou-Jen Liu, Jian Peng, Alexander G. Schwing

2019-04-11

A zoo of deep nets is available these days for almost any given task, and it is increasingly unclear which net to start with when addressing a new task, or which net to use as an initialization for fine-tuning a new model. To address this issue, in this paper, we develop knowledge flow which moves 'knowledge' from multiple deep nets, referred to as teachers, to a new deep net model, called the student. The structure of the teachers and the student can differ arbitrarily and they can be trained on entirely different tasks with different output spaces too. Upon training with knowledge flow the student is independent of the teachers. We demonstrate our approach on a variety of supervised and reinforcement learning tasks, outperforming fine-tuning and other 'knowledge exchange' methods.

A Simple Baseline for Audio-Visual Scene-Aware Dialog (1904.05876v1)

Idan Schwartz, Alexander Schwing, Tamir Hazan

2019-04-11

The recently proposed audio-visual scene-aware dialog task paves the way to a more data-driven way of learning virtual assistants, smart speakers and car navigation systems. However, very little is known to date about how to effectively extract meaningful information from a plethora of sensors that pound the computational engine of those devices. Therefore, in this paper, we provide and carefully analyze a simple baseline for audio-visual scene-aware dialog which is trained end-to-end. Our method differentiates in a data-driven manner useful signals from distracting ones using an attention mechanism. We evaluate the proposed approach on the recently introduced and challenging audio-visual scene-aware dataset, and demonstrate the key features that permit to outperform the current state-of-the-art by more than 20% on CIDEr.

KeyIn: Discovering Subgoal Structure with Keyframe-based Video Prediction (1904.05869v1)

Karl Pertsch, Oleh Rybkin, Jingyun Yang, Kosta Derpanis, Joseph Lim, Kostas Daniilidis, Andrew Jaegle

2019-04-11

Real-world image sequences can often be naturally decomposed into a small number of frames depicting interesting, highly stochastic moments (its ) and the low-variance frames in between them. In image sequences depicting trajectories to a goal, keyframes can be seen as capturing the of the sequence as they depict the high-variance moments of interest that ultimately led to the goal. In this paper, we introduce a video prediction model that discovers the keyframe structure of image sequences in an unsupervised fashion. We do so using a hierarchical Keyframe-Intermediate model (KeyIn) that stochastically predicts keyframes and their offsets in time and then uses these predictions to deterministically predict the intermediate frames. We propose a differentiable formulation of this problem that allows us to train the full hierarchical model using a sequence reconstruction loss. We show that our model is able to find meaningful keyframe structure in a simulated dataset of robotic demonstrations and that these keyframes can serve as subgoals for planning. Our model outperforms other hierarchical prediction approaches for planning on a simulated pushing task.

Connections Between Adaptive Control and Optimization in Machine Learning (1904.05856v1)

Joseph E. Gaudio, Travis E. Gibson, Anuradha M. Annaswamy, Michael A. Bolender, Eugene Lavretsky

2019-04-11

This paper demonstrates many immediate connections between adaptive control and optimization methods commonly employed in machine learning. Starting from common output error formulations, similarities in update law modifications are examined. Concepts in stability, performance, and learning, common to both fields are then discussed. Building on the similarities in update laws and common concepts, new intersections and opportunities for improved algorithm analysis are provided. In particular, a specific problem related to higher order learning is solved through insights obtained from these intersections.

Adversarial Autoencoders with Constant-Curvature Latent Manifolds (1812.04314v2)

Daniele Grattarola, Lorenzo Livi, Cesare Alippi

2018-12-11

Constant-curvature Riemannian manifolds (CCMs) have been shown to be ideal embedding spaces in many application domains, as their non-Euclidean geometry can naturally account for some relevant properties of data, like hierarchy and circularity. In this work, we introduce the CCM adversarial autoencoder (CCM-AAE), a probabilistic generative model trained to represent a data distribution on a CCM. Our method works by matching the aggregated posterior of the CCM-AAE with a probability distribution defined on a CCM, so that the encoder implicitly learns to represent data on the CCM to fool the discriminator network. The geometric constraint is also explicitly imposed by jointly training the CCM-AAE to maximise the membership degree of the embeddings to the CCM. While a few works in recent literature make use of either hyperspherical or hyperbolic manifolds for different learning tasks, ours is the first unified framework to seamlessly deal with CCMs of different curvatures. We show the effectiveness of our model on three different datasets characterised by non-trivial geometry: semi-supervised classification on MNIST, link prediction on two popular citation datasets, and graph-based molecule generation using the QM9 chemical database. Results show that our method improves upon other autoencoders based on Euclidean and non-Euclidean geometries on all tasks taken into account.

Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds (1805.06299v3)

Daniele Grattarola, Daniele Zambon, Cesare Alippi, Lorenzo Livi

2018-05-16

The space of graphs is often characterised by a non-trivial geometry, which complicates learning and inference in practical applications. A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces have often been shown to be better suited for embedding graphs. Among these, constant-curvature Riemannian manifolds (CCMs) offer embedding spaces suitable for studying the statistical properties of a graph distribution, as they provide ways to easily compute metric geodesic distances. In this paper, we focus on the problem of detecting changes in stationarity in a stream of attributed graphs. To this end, we introduce a novel change detection framework based on neural networks and CCMs, that takes into account the non-Euclidean nature of graphs. Our contribution in this work is twofold. First, via a novel approach based on adversarial learning, we compute graph embeddings by training an autoencoder to represent graphs on CCMs. Second, we introduce two novel change detection tests operating on CCMs. We perform experiments on synthetic data, as well as two real-world application scenarios: the detection of epileptic seizures using functional connectivity brain networks, and the detection of hostility between two subjects, using human skeletal graphs. Results show that the proposed methods are able to detect even small changes in a graph-generating process, consistently outperforming approaches based on Euclidean embeddings.

Three-Dimensional Dose Prediction for Lung IMRT Patients with Deep Neural Networks: Robust Learning from Heterogeneous Beam Configurations (1812.06934v2)

Ana M. Barragan-Montero, Dan Nguyen, Weiguo Lu, Mu-Han Lin, Xavier Geets, Edmond Sterpin, Steve Jiang

2018-12-17

The use of neural networks to directly predict three-dimensional dose distributions for automatic planning is becoming popular. However, the existing methods only use patient anatomy as input and assume consistent beam configuration for all patients in the training database. The purpose of this work is to develop a more general model that, in addition to patient anatomy, also considers variable beam configurations, to achieve a more comprehensive automatic planning with a potentially easier clinical implementation, without the need of training specific models for different beam settings.

ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission (1904.05342v2)

Kexin Huang, Jaan Altosaar, Rajesh Ranganath

2019-04-10

Clinical notes contain information about patients that goes beyond structured data like lab values and medications. However, clinical notes have been underused relative to structured data, because notes are high-dimensional and sparse. This work develops and evaluates representations of clinical notes using bidirectional transformers (ClinicalBERT). ClinicalBERT uncovers high-quality relationships between medical concepts as judged by humans. ClinicalBert outperforms baselines on 30-day hospital readmission prediction using both discharge summaries and the first few days of notes in the intensive care unit. Code and model parameters are available.

---