Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data
Seoul National University（首尔国立大学）；Kakao Brain
Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo, Byoung-Tak Zhang
备注：
8 pages, 3 figures, Association for the Advancement of Artificial Intelligence (AAAI2020). arXiv admin note: substantial text overlap with arXiv:1907.01709
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex dependency structures that imply variable-length semantic flows and their compositions, and those are hard to be captured by conventional methods. Here, we propose Cut-Based Graph Learning Networks (CB-GLNs) for learning video data by discovering these complex structures of the video. The CB-GLNs represent video data as a graph, with nodes and edges corresponding to frames of the video and their dependencies respectively. The CB-GLNs find compositional dependencies of the data in multilevel graph forms via a parameterized kernel with graph-cut and a message passing framework. We evaluate the proposed method on the two different tasks for video understanding: Video theme classification (Youtube-8M dataset) and Video Question and Answering (TVQA dataset). The experimental results show that our model efficiently learns the semantic compositional structure of video data. Furthermore, our model achieves the highest performance in comparison to other baseline methods.
University of Toronto（多伦多大学）；Vector Institute（Vector研究所）
In this work, we focus on an analogical reasoning task that contains rich compositional structures, Raven's Progressive Matrices (RPM). To discover compositional structures of the data, we propose the Scattering Compositional Learner (SCL), an architecture that composes neural networks in a sequence. Our SCL achieves state-of-the-art performance on two RPM datasets, with a 48.7% relative improvement on Balanced-RAVEN and 26.4% on PGM over the previous state-of-the-art. We additionally show that our model discovers compositional representations of objects' attributes (e.g., shape color, size), …
Johns Hopkins University（约翰斯·霍普金斯大学）；Microsoft Research（微软研究院）；New York University（纽约大学）
How can neural networks perform so well on compositional tasks even though they lack explicit compositional representations? We use a novel analysis technique called ROLE to show that recurrent neural networks perform well on such tasks by converging to solutions which implicitly represent symbolic structure. This method uncovers a symbolic structure which, when properly embedded in vector space, closely approximates the encodings of a standard seq2seq network trained to perform the compositional SCAN task. We verify the causal importance of the discovered symbolic structure by showing that, w…
Despite its importance, choosing the structural form of the kernel in nonparametric regression remains a black art. We define a space of kernel structures which are built compositionally by adding and multiplying a small number of base kernels. We present a method for searching over this space of structures which mirrors the scientific discovery process. The learned structures can often decompose functions into interpretable components and enable long-range extrapolation on time-series datasets. Our structure search method outperforms many widely used kernels and kernel combination methods on …
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex temporal dependencies that imply variable-length semantic flows and their compositions, and those are hard to be captured by conventional methods. Here, we propose Temporal Dependency Networks (TDNs) for learning video data by discovering these complex structures of the videos. The TDNs represent video as a graph whose nodes and edges correspond to frames of …
CIMeC, University of Trento（特伦托大学心智/脑科学中心）；ICREA（加泰罗尼亚研究与高等教育学院）；Facebook AI Research（脸书人工智能研究院）
Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of "jump around" 0-shot from the component words. Recurrent networks (RNNs) were found to completely fail the most challenging generalization cases. We test here a convolutional network (CNN) on these tasks, reporting hugely improved performance with respect to RNNs. Despite the big improvement, the CNN has however not induced systematic rules, suggesting that the difference between compositional and non-compositional behaviour is not …
Facebook Artificial Intelligence Research（脸书人工智能研究院）；Istituto Italiano di Tecnologia（意大利理工学院）
Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared by different tasks, and recombining them to solve new problems. In this paper, we explore the compositional generalization capabilities of recurrent neural networks (RNNs). We first propose the lookup table composition domain as a simple setup to test compositional behaviour and show that it is theoretically possible for a standard RNN to learn to behave com…
University of Pennsylvania（宾夕法尼亚大学）；Brown University（布朗大学）
A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and reuse them in novel combinations for solving different problems. Learning such compositional structures has been a challenge for artificial systems, due to the underlying combinatorial search. To date, research into compositional learning has largely proceeded separately from work on lifelong or continual learning. This dissertation integrated these two lines of work to present a general-purpose framework for lifelong learning of functionally compositional structures. The framework separates the…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Uber Advanced Technologies Group（优步先进技术集团）
The generalization properties of Gaussian processes depend heavily on the choice of kernel, and this choice remains a dark art. We present the Neural Kernel Network (NKN), a flexible family of kernels represented by a neural network. The NKN architecture is based on the composition rules for kernels, so that each unit of the network corresponds to a valid kernel. It can compactly approximate compositional kernel structures such as those used by the Automatic Statistician (Lloyd et al., 2014), but because the architecture is differentiable, it is end-to-end trainable with gradient-based optimiz…
University of Tübingen（图宾根大学）；University of Bath（巴斯大学）；Electronic Arts（艺电公司）；Siemens AG（西门子股份公司）；TU Munich（慕尼黑工业大学）；University of Bristol（布里斯托尔大学）；Royal Society（皇家学会）
Gaussian processes (GPs) are nonparametric priors over functions. Fitting a GP implies computing a posterior distribution of functions consistent with the observed data. Similarly, deep Gaussian processes (DGPs) should allow us to compute a posterior distribution of compositions of multiple functions giving rise to the observations. However, exact Bayesian inference is intractable for DGPs, motivating the use of various approximations. We show that the application of simplifying mean-field assumptions across the hierarchy leads to the layers of a DGP collapsing to near-deterministic transforma…
Does Data Scaling Lead to Visual Compositional Generalization?
Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学）；Technical University of Munich（慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Max Planck Institute for Intelligent Systems, Tübingen（马克斯·普朗克智能系统研究所，图宾根）
University of Amsterdam（阿姆斯特丹大学）；DeepMind（深度思维）；Georgia Institute of Technology（佐治亚理工学院）；Facebook AI Research（Facebook人工智能研究院）
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential data that can be re-composed and executed to perform new tasks. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate CompILE in a challenging 2D multi-task environment and a continuous control task, …
University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；Northeastern University（东北大学）
Existing methods for structure discovery in time series data construct interpretable, compositional kernels for Gaussian process regression models. While the learned Gaussian process model provides posterior mean and variance estimates, typically the structure is learned via a greedy optimization procedure. This restricts the space of possible solutions and leads to over-confident uncertainty estimates. We introduce a fully Bayesian approach, inferring a full posterior over structures, which more reliably captures the uncertainty of the model.
We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images. The building blocks are binary features defined hierarchically as a composition of some of the features in the layer immediately below, arranged in a particular manner. At a high level, HCN is similar to a sigmoid belief network with pooling. Inference and learning in HCN are very challenging and existing variational approximations do not work satisfactorily. A main contribution of this work is to show that …
Tsinghua University（清华大学）；Institute for Brain and Cognitive Science, Tsinghua University (THUIBCS)（清华大学脑与认知科学研究所）；Chinese PLA General Hospital（中国人民解放军总医院）
Causal discovery from time-series data has been a central task in machine learning. Recently, Granger causality inference is gaining momentum due to its good explainability and high compatibility with emerging deep neural networks. However, most existing methods assume structured input data and degenerate greatly when encountering data with randomly missing entries or non-uniform sampling frequencies, which hampers their applications in real scenarios. To address this issue, here we present CUTS, a neural Granger causal discovery algorithm to jointly impute unobserved data points and build cau…
Recent work in NLP shows that LSTM language models capture compositional structure in language data. For a closer look at how these representations are composed hierarchically, we present a novel measure of interdependence between word meanings in an LSTM, based on their interactions at the internal gates. To explore how compositional representations arise over training, we conduct simple experiments on synthetic data, which illustrate our measure by showing how high interdependence can hurt generalization. These synthetic experiments also illustrate a specific hypothesis about how hierarchica…
