January 26, 2020

2932 words 14 mins read

Paper Group ANR 1577

Understanding and Stabilizing GANs’ Training Dynamics with Control Theory. Improving 3D U-Net for Brain Tumor Segmentation by Utilizing Lesion Prior. Scalable Cross-Lingual Transfer of Neural Sentence Embeddings. Gradient Boosting Survival Tree with Applications in Credit Scoring. Risk-Averse Trust Region Optimization for Reward-Volatility Reductio …

Understanding and Stabilizing GANs’ Training Dynamics with Control Theory


Title	Understanding and Stabilizing GANs’ Training Dynamics with Control Theory
Authors	Kun Xu, Chongxuan Li, Huanshu Wei, Jun Zhu, Bo Zhang
Abstract	Generative adversarial networks~(GANs) have made significant progress on realistic image generation but often suffer from instability during the training process. Most previous analyses mainly focus on the equilibrium that GANs achieve, whereas a gap exists between such theoretical analyses and practical implementations, where it is the training dynamics that plays a vital role in the convergence and stability of GANs. In this paper, we directly model the dynamics of GANs and adopt the control theory to understand and stabilize it. Specifically, we interpret the training process of various GANs as certain types of dynamics in a unified perspective of control theory which enables us to model the stability and convergence easily. Borrowed from control theory, we adopt the widely-used negative feedback control to stabilize the training dynamics, which can be considered as an $L2$ regularization on the output of the discriminator. We empirically verify our method on both synthetic data and natural image datasets. The results demonstrate that our method can stabilize the training dynamics as well as converge better than baselines.
Tasks	Image Generation, L2 Regularization
Published	2019-09-29
URL	https://arxiv.org/abs/1909.13188v1
PDF	https://arxiv.org/pdf/1909.13188v1.pdf
PWC	https://paperswithcode.com/paper/understanding-and-stabilizing-gans-training
Repo
Framework

Improving 3D U-Net for Brain Tumor Segmentation by Utilizing Lesion Prior


Title	Improving 3D U-Net for Brain Tumor Segmentation by Utilizing Lesion Prior
Authors	Po-Yu Kao, Jefferson W. Chen, B. S. Manjunath
Abstract	We propose a novel, simple and effective method to integrate lesion prior and a 3D U-Net for improving brain tumor segmentation. First, we utilize the ground-truth brain tumor lesions from a group of patients to generate the heatmaps of different types of lesions. These heatmaps are used to create the volume-of-interest (VOI) map which contains prior information about brain tumor lesions. The VOI map is then integrated with the multimodal MR images and input to a 3D U-Net for segmentation. The proposed method is evaluated on a public benchmark dataset, and the experimental results show that the proposed feature fusion method achieves an improvement over the baseline methods. In addition, our proposed method also achieves a competitive performance compared to state-of-the-art methods.
Tasks	Brain Tumor Segmentation
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00281v3
PDF	https://arxiv.org/pdf/1907.00281v3.pdf
PWC	https://paperswithcode.com/paper/improving-3d-u-net-for-brain-tumor
Repo
Framework

Scalable Cross-Lingual Transfer of Neural Sentence Embeddings


Title	Scalable Cross-Lingual Transfer of Neural Sentence Embeddings
Authors	Hanan Aldarmaki, Mona Diab
Abstract	We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models. We evaluate three alignment frameworks applied to these models: joint modeling, representation transfer learning, and sentence mapping, using parallel text to guide the alignment. Our results support representation transfer as a scalable approach for modular cross-lingual alignment of neural sentence embeddings, where we observe better performance compared to joint models in intrinsic and extrinsic evaluations, particularly with smaller sets of parallel data.
Tasks	Cross-Lingual Transfer, Sentence Embedding, Sentence Embeddings, Transfer Learning
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05542v1
PDF	http://arxiv.org/pdf/1904.05542v1.pdf
PWC	https://paperswithcode.com/paper/scalable-cross-lingual-transfer-of-neural
Repo
Framework

Gradient Boosting Survival Tree with Applications in Credit Scoring


Title	Gradient Boosting Survival Tree with Applications in Credit Scoring
Authors	Miaojun Bai, Yan Zheng, Yun Shen
Abstract	Credit scoring plays a vital role in the field of consumer finance. Survival analysis provides an advanced solution to the credit-scoring problem by quantifying the probability of survival time. In order to deal with highly heterogeneous industrial data collected in Chinese market of consumer finance, we propose a nonparametric ensemble tree model called gradient boosting survival tree (GBST) that extends the survival tree models with a gradient boosting algorithm. The survival tree ensemble is learned by minimizing the negative log-likelihood in an additive manner. The proposed model optimizes the survival probability simultaneously for each time period, which can reduce the overall error significantly. % Second, the model aggregates progressively the survival probability, which ensures the monotonicity of the survival function. Finally, as a test of the applicability, we apply the GBST model to quantify the credit risk with large-scale real market data. The results show that the GBST model outperforms the existing survival models measured by the concordance index (C-index), Kolmogorov-Smirnov (KS) index, as well as by the area under the receiver operating characteristic curve (AUC) of each time period.
Tasks	Survival Analysis
Published	2019-08-09
URL	https://arxiv.org/abs/1908.03385v3
PDF	https://arxiv.org/pdf/1908.03385v3.pdf
PWC	https://paperswithcode.com/paper/gradient-boosting-survival-tree-with
Repo
Framework

Risk-Averse Trust Region Optimization for Reward-Volatility Reduction


Title	Risk-Averse Trust Region Optimization for Reward-Volatility Reduction
Authors	Lorenzo Bisi, Luca Sabbioni, Edoardo Vittori, Matteo Papini, Marcello Restelli
Abstract	In real-world decision-making problems, for instance in the fields of finance, robotics or autonomous driving, keeping uncertainty under control is as important as maximizing expected returns. Risk aversion has been addressed in the reinforcement learning literature through risk measures related to the variance of returns. However, in many cases, the risk is measured not only on a long-term perspective, but also on the step-wise rewards (e.g., in trading, to ensure the stability of the investment bank, it is essential to monitor the risk of portfolio positions on a daily basis). In this paper, we define a novel measure of risk, which we call reward volatility, consisting of the variance of the rewards under the state-occupancy measure. We show that the reward volatility bounds the return variance so that reducing the former also constrains the latter. We derive a policy gradient theorem with a new objective function that exploits the mean-volatility relationship, and develop an actor-only algorithm. Furthermore, thanks to the linearity of the Bellman equations defined under the new objective function, it is possible to adapt the well-known policy gradient algorithms with monotonic improvement guarantees such as TRPO in a risk-averse manner. Finally, we test the proposed approach in two simulated financial environments.
Tasks	Autonomous Driving, Decision Making
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03193v1
PDF	https://arxiv.org/pdf/1912.03193v1.pdf
PWC	https://paperswithcode.com/paper/risk-averse-trust-region-optimization-for
Repo
Framework

Ranking-Based Autoencoder for Extreme Multi-label Classification


Title	Ranking-Based Autoencoder for Extreme Multi-label Classification
Authors	Bingyu Wang, Li Chen, Wei Sun, Kechen Qin, Kefeng Li, Hui Zhou
Abstract	Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features and instances could be thousands or millions. XML is more and more on demand in the Internet industries, accompanied with the increasing business scale / scope and data accumulation. The extremely large label collections yield challenges such as computational complexity, inter-label dependency and noisy labeling. Many methods have been proposed to tackle these challenges, based on different mathematical formulations. In this paper, we propose a deep learning XML method, with a word-vector-based self-attention, followed by a ranking-based AutoEncoder architecture. The proposed method has three major advantages: 1) the autoencoder simultaneously considers the inter-label dependencies and the feature-label dependencies, by projecting labels and features onto a common embedding space; 2) the ranking loss not only improves the training efficiency and accuracy but also can be extended to handle noisy labeled data; 3) the efficient attention mechanism improves feature representation by highlighting feature importance. Experimental results on benchmark datasets show the proposed method is competitive to state-of-the-art methods.
Tasks	Extreme Multi-Label Classification, Feature Importance, Multi-Label Classification
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05937v1
PDF	http://arxiv.org/pdf/1904.05937v1.pdf
PWC	https://paperswithcode.com/paper/ranking-based-autoencoder-for-extreme-multi
Repo
Framework

Kinetic Market Model: An Evolutionary Algorithm


Title	Kinetic Market Model: An Evolutionary Algorithm
Authors	Evandro Luquini, Nizam Omar
Abstract	This research proposes the econophysics kinetic market model as an evolutionary algorithm’s instance. The immediate results from this proposal is a new replacement rule for family competition genetic algorithms. It also represents a starting point to adding evolvable entities to kinetic market models.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01241v1
PDF	https://arxiv.org/pdf/1906.01241v1.pdf
PWC	https://paperswithcode.com/paper/kinetic-market-model-an-evolutionary
Repo
Framework

Learning Non-Parametric Invariances from Data with Permanent Random Connectomes


Title	Learning Non-Parametric Invariances from Data with Permanent Random Connectomes
Authors	Dipan K. Pal, Akshay Chawla, Marios Savvides
Abstract	One of the fundamental problems in supervised classification and in machine learning in general, is the modelling of non-parametric invariances that exist in data. Most prior art has focused on enforcing priors in the form of invariances to parametric nuisance transformations that are expected to be present in data. Learning non-parametric invariances directly from data remains an important open problem. In this paper, we introduce a new architectural layer for convolutional networks which is capable of learning general invariances from data itself. This layer can learn invariance to non-parametric transformations and interestingly, motivates and incorporates permanent random connectomes, thereby being called Permanent Random Connectome Non-Parametric Transformation Networks (PRC-NPTN). PRC-NPTN networks are initialized with random connections (not just weights) which are a small subset of the connections in a fully connected convolution layer. Importantly, these connections in PRC-NPTNs once initialized remain permanent throughout training and testing. Permanent random connectomes make these architectures loosely more biologically plausible than many other mainstream network architectures which require highly ordered structures. We motivate randomly initialized connections as a simple method to learn invariance from data itself while invoking invariance towards multiple nuisance transformations simultaneously. We find that these randomly initialized permanent connections have positive effects on generalization, outperform much larger ConvNet baselines and the recently proposed Non-Parametric Transformation Network (NPTN) on benchmarks that enforce learning invariances from the data itself.
Tasks
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05266v2
PDF	https://arxiv.org/pdf/1911.05266v2.pdf
PWC	https://paperswithcode.com/paper/learning-non-parametric-invariances-from-data
Repo
Framework

Randomized Computer Vision Approaches for Pattern Recognition in Timepix and Timepix3 Detectors


Title	Randomized Computer Vision Approaches for Pattern Recognition in Timepix and Timepix3 Detectors
Authors	Petr Mánek, Benedikt Bergmann, Petr Burian, Lukáš Meduna, Stanislav Pospíšil, Michal Suk
Abstract	Timepix and Timepix3 are hybrid pixel detectors ($256\times 256$ pixels), capable of tracking ionizing particles as isolated clusters of pixels. To efficiently analyze such clusters at potentially high rates, we introduce multiple randomized pattern recognition algorithms inspired by computer vision. Offering desirable probabilistic bounds on accuracy and complexity, the presented methods are well-suited for use in real-time applications, and some may even be modified to tackle trans-dimensional problems. In Timepix detectors, which do not support data-driven acquisition, they have been shown to correctly separate clusters of overlapping tracks. In Timepix3 detectors, simultaneous acquisition of Time-of-Arrival (ToA) and Time-over-Threshold (ToT) pixel data enables reconstruction of the depth, transitioning from 2D to 3D point clouds. The presented algorithms have been tested on simulated inputs, test beam data from the Heidelberg Ion therapy Center and the Super Proton Synchrotron and were applied to data acquired in the MoEDAL and ATLAS experiments at CERN.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02367v1
PDF	https://arxiv.org/pdf/1911.02367v1.pdf
PWC	https://paperswithcode.com/paper/randomized-computer-vision-approaches-for
Repo
Framework

A Survey on Session-based Recommender Systems


Title	A Survey on Session-based Recommender Systems
Authors	Shoujin Wang, Longbing Cao, Yan Wang
Abstract	Session-based recommender systems (SBRS) are an emerging topic in the recommendation domain and have attracted much attention from both academia and industry in recent years. Most of existing works only work on modelling the general item-level dependency for recommendation tasks. However, there are many more other challenges at different levels, e.g., item feature level and session level, and from various perspectives, e.g., item heterogeneity and intra- and inter-item feature coupling relations, associated with SBRS. In this paper, we provide a systematic and comprehensive review on SBRS and create a hierarchical and in-depth understanding of a variety of challenges in SBRS. To be specific, we first illustrate the value and significance of SBRS, followed by a hierarchical framework to categorize the related research issues and methods of SBRS and to reveal its intrinsic challenges and complexities. Further, a summary together with a detailed introduction of the research progress is provided. Lastly, we share some prospects in this research area.
Tasks	Recommendation Systems
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04864v1
PDF	http://arxiv.org/pdf/1902.04864v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-session-based-recommender-systems
Repo
Framework

Learning to Optimally Segment Point Clouds


Title	Learning to Optimally Segment Point Clouds
Authors	Peiyun Hu, David Held, Deva Ramanan
Abstract	We focus on the problem of class-agnostic instance segmentation of LiDAR point clouds. We propose an approach that combines graph-theoretic search with data-driven learning: it searches over a set of candidate segmentations and returns one where individual segments score well according to a data-driven point-based model of “objectness”. We prove that if we score a segmentation by the worst objectness among its individual segments, there is an efficient algorithm that finds the optimal worst-case segmentation among an exponentially large number of candidate segmentations. We also present an efficient algorithm for the average-case. For evaluation, we repurpose KITTI 3D detection as a segmentation benchmark and empirically demonstrate that our algorithms significantly outperform past bottom-up segmentation approaches and top-down object-based algorithms on segmenting point clouds.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04976v1
PDF	https://arxiv.org/pdf/1912.04976v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-optimally-segment-point-clouds
Repo
Framework

Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following


Title	Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following
Authors	Geoffrey Cideron, Mathieu Seurin, Florian Strub, Olivier Pietquin
Abstract	Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. These properties make it a natural fit to guide the training of interactive agents as it could ease recurrent challenges in Reinforcement Learning such as sample complexity, generalization, or multi-tasking. Yet, it remains an open-problem to relate language and RL in even simple instruction following scenarios. Current methods rely on expert demonstrations, auxiliary losses, or inductive biases in neural architectures. In this paper, we propose an orthogonal approach called Textual Hindsight Experience Replay (THER) that extends the Hindsight Experience Replay approach to the language setting. Whenever the agent does not fulfill its instruction, THER learns to output a new directive that matches the agent trajectory, and it relabels the episode with a positive reward. To do so, THER learns to map a state into an instruction by using past successful trajectories, which removes the need to have external expert interventions to relabel episodes as in vanilla HER. We observe that this simple idea also initiates a learning synergy between language acquisition and policy learning on instruction following tasks in the BabyAI environment.
Tasks	Language Acquisition
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09451v2
PDF	https://arxiv.org/pdf/1910.09451v2.pdf
PWC	https://paperswithcode.com/paper/self-educated-language-agent-with-hindsight-1
Repo
Framework

An Improved Analysis of Training Over-parameterized Deep Neural Networks


Title	An Improved Analysis of Training Over-parameterized Deep Neural Networks
Authors	Difan Zou, Quanquan Gu
Abstract	A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the condition on the width of the neural network to ensure the global convergence is very stringent, which is often a high-degree polynomial in the training sample size $n$ (e.g., $O(n^{24})$). In this paper, we provide an improved analysis of the global convergence of (stochastic) gradient descent for training deep neural networks, which only requires a milder over-parameterization condition than previous work in terms of the training sample size and other problem-dependent parameters. The main technical contributions of our analysis include (a) a tighter gradient lower bound that leads to a faster convergence of the algorithm, and (b) a sharper characterization of the trajectory length of the algorithm. By specializing our result to two-layer (i.e., one-hidden-layer) neural networks, it also provides a milder over-parameterization condition than the best-known result in prior work.
Tasks
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04688v1
PDF	https://arxiv.org/pdf/1906.04688v1.pdf
PWC	https://paperswithcode.com/paper/an-improved-analysis-of-training-over
Repo
Framework

Explicit Spatial Encoding for Deep Local Descriptors


Title	Explicit Spatial Encoding for Deep Local Descriptors
Authors	Arun Mukundan, Giorgos Tolias, Ondrej Chum
Abstract	We propose a kernelized deep local-patch descriptor based on efficient match kernels of neural network activations. Response of each receptive field is encoded together with its spatial location using explicit feature maps. Two location parametrizations, Cartesian and polar, are used to provide robustness to a different types of canonical patch misalignment. Additionally, we analyze how the conventional architecture, i.e. a fully connected layer attached after the convolutional part, encodes responses in a spatially variant way. In contrary, explicit spatial encoding is used in our descriptor, whose potential applications are not limited to local-patches. We evaluate the descriptor on standard benchmarks. Both versions, encoding 32x32 or 64x64 patches, consistently outperform all other methods on all benchmarks. The number of parameters of the model is independent of the input patch resolution.
Tasks
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07190v1
PDF	http://arxiv.org/pdf/1904.07190v1.pdf
PWC	https://paperswithcode.com/paper/explicit-spatial-encoding-for-deep-local
Repo
Framework

Intelligent architectures for robotics: The merging of cognition and emotion


Title	Intelligent architectures for robotics: The merging of cognition and emotion
Authors	Luiz Pessoa
Abstract	What is the place of emotion in intelligent robots? In the past two decades, researchers have advocated for the inclusion of some emotion-related components in the general information processing architecture of autonomous agents, say, for better communication with humans, or to instill a sense of urgency to action. The framework advanced here goes beyond these approaches and proposes that emotion and motivation need to be integrated with all aspects of the architecture. Thus, cognitive-emotional integration is a key design principle. Emotion is not an “add on” that endows a robot with “feelings” (for instance, reporting or expressing its internal state). It allows the significance of percepts, plans, and actions to be an integral part of all its computations. It is hypothesized that a sophisticated artificial intelligence cannot be built from separate cognitive and emotional modules. A hypothetical test inspired by the Turing test, called the Dolores test, is proposed to test this assertion.
Tasks
Published	2019-02-01
URL	http://arxiv.org/abs/1902.00363v1
PDF	http://arxiv.org/pdf/1902.00363v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-architectures-for-robotics-the
Repo
Framework