Paper Group ANR 329
A geometric interpretation of stochastic gradient descent using diffusion metrics. Single Image Reflection Removal with Physically-based Rendering. From explanation to synthesis: Compositional program induction for learning from demonstration. Classification As Decoder: Trading Flexibility For Control In Neural Dialogue. Reliable training and estim …
A geometric interpretation of stochastic gradient descent using diffusion metrics
| Title | A geometric interpretation of stochastic gradient descent using diffusion metrics |
| Authors | R. Fioresi, P. Chaudhari, S. Soatto |
| Abstract | Stochastic gradient descent (SGD) is a key ingredient in the training of deep neural networks and yet its geometrical significance appears elusive. We study a deterministic model in which the trajectories of our dynamical systems are described via geodesics of a family of metrics arising from the diffusion matrix. These metrics encode information about the highly non-isotropic gradient noise in SGD. We establish a parallel with General Relativity models, where the role of the electromagnetic field is played by the gradient of the loss function. We compute an example of a two layer network. |
| Tasks | |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12194v1 |
| https://arxiv.org/pdf/1910.12194v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-geometric-interpretation-of-stochastic |
| Repo | |
| Framework | |
Single Image Reflection Removal with Physically-based Rendering
| Title | Single Image Reflection Removal with Physically-based Rendering |
| Authors | Soomin Kim, Yuchi Huo, Sung-Eui Yoon |
| Abstract | Recently, deep learning based single image reflection separation methods have been exploited widely. To benefit the learning approach, a large number of training image pairs (i.e., with and without reflections) were synthesized in various ways, yet they are away from a physically-based direction. In this paper, physically based rendering is used for faithfully synthesizing the required training images, and corresponding network structure is proposed. We utilize existing image data to estimate mesh, then physically simulate the depth-dependent light transportation between mesh, glass, and lens with path tracing. For guiding the separation better, we additionally consider a module of removing complicated ghosting and blurring glass-effects, which allows obtaining priori information before having the glass distortion. This module is easily accommodated within our approach, since that prior information can be physically generated by our rendering process. The proposed method considering the priori information as well as the existing posterior information is validated with various real reflection images, and is demonstrated to show visually pleasant and numerically better results compared to the state-of-theart techniques. |
| Tasks | |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11934v1 |
| http://arxiv.org/pdf/1904.11934v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-reflection-removal-with |
| Repo | |
| Framework | |
From explanation to synthesis: Compositional program induction for learning from demonstration
| Title | From explanation to synthesis: Compositional program induction for learning from demonstration |
| Authors | Michael Burke, Svetlin Penkov, Subramanian Ramamoorthy |
| Abstract | Hybrid systems are a compact and natural mechanism with which to address problems in robotics. This work introduces an approach to learning hybrid systems from demonstrations, with an emphasis on extracting models that are explicitly verifiable and easily interpreted by robot operators. We fit a sequence of controllers using sequential importance sampling under a generative switching proportional controller task model. Here, we parameterise controllers using a proportional gain and a visually verifiable joint angle goal. Inference under this model is challenging, but we address this by introducing an attribution prior extracted from a neural end-to-end visuomotor control model. Given the sequence of controllers comprising a task, we simplify the trace using grammar parsing strategies, taking advantage of the sequence compositionality, before grounding the controllers by training perception networks to predict goals given images. Using this approach, we are successfully able to induce a program for a visuomotor reaching task involving loops and conditionals from a single demonstration and a neural end-to-end model. In addition, we are able to discover the program used for a tower building task. We argue that computer program-like control systems are more interpretable than alternative end-to-end learning approaches, and that hybrid systems inherently allow for better generalisation across task configurations. |
| Tasks | |
| Published | 2019-02-27 |
| URL | https://arxiv.org/abs/1902.10657v2 |
| https://arxiv.org/pdf/1902.10657v2.pdf | |
| PWC | https://paperswithcode.com/paper/from-explanation-to-synthesis-compositional |
| Repo | |
| Framework | |
Classification As Decoder: Trading Flexibility For Control In Neural Dialogue
| Title | Classification As Decoder: Trading Flexibility For Control In Neural Dialogue |
| Authors | Sam Shleifer, Manish Chablani, Namit Katariya, Anitha Kannan, Xavier Amatriain |
| Abstract | Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deep understanding of conversational context, and generate a wide variety of responses. This flexibility comes at the cost of control. Undesirable responses in the training data will be reproduced by the model at inference time, and longer generations often don’t make sense. Instead of generating responses one word at a time, we train a classifier to choose from a predefined list of full responses. The classifier is trained on (conversation context, response class) pairs, where each response class is a noisily labeled group of interchangeable responses. At inference, we generate the exemplar response associated with the predicted response class. Experts can edit and improve these exemplar responses over time without retraining the classifier or invalidating old training data. Human evaluation of 775 unseen doctor/patient conversations shows that this tradeoff improves responses. Only 12% of our discriminative approach’s responses are worse than the doctor’s response in the same conversational context, compared to 18% for the generative model. A discriminative model trained without any manual labeling of response classes achieves equal performance to the generative model. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.03476v3 |
| https://arxiv.org/pdf/1910.03476v3.pdf | |
| PWC | https://paperswithcode.com/paper/classification-as-decoder-trading-flexibility |
| Repo | |
| Framework | |
Reliable training and estimation of variance networks
| Title | Reliable training and estimation of variance networks |
| Authors | Nicki S. Detlefsen, Martin Jørgensen, Søren Hauberg |
| Abstract | We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks. We derive a locally aware mini-batching scheme that result in sparse robust gradients, and show how to make unbiased weight updates to a variance network. Further, we formulate a heuristic for robustly fitting both the mean and variance networks post hoc. Finally, we take inspiration from posterior Gaussian processes and propose a network architecture with similar extrapolation properties to Gaussian processes. The proposed methodologies are complementary, and improve upon baseline methods individually. Experimentally, we investigate the impact on predictive uncertainty on multiple datasets and tasks ranging from regression, active learning and generative modeling. Experiments consistently show significant improvements in predictive uncertainty estimation over state-of-the-art methods across tasks and datasets. |
| Tasks | Active Learning, Gaussian Processes |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.03260v2 |
| https://arxiv.org/pdf/1906.03260v2.pdf | |
| PWC | https://paperswithcode.com/paper/reliable-training-and-estimation-of-variance |
| Repo | |
| Framework | |
Fair-by-design explainable models for prediction of recidivism
| Title | Fair-by-design explainable models for prediction of recidivism |
| Authors | Eduardo Soares, Plamen Angelov |
| Abstract | Recidivism prediction provides decision makers with an assessment of the likelihood that a criminal defendant will reoffend that can be used in pre-trial decision-making. It can also be used for prediction of locations where crimes most occur, profiles that are more likely to commit violent crimes. While such instruments are gaining increasing popularity, their use is controversial as they may present potential discriminatory bias in the risk assessment. In this paper we propose a new fair-by-design approach to predict recidivism. It is prototype-based, learns locally and extracts empirically the data distribution. The results show that the proposed method is able to reduce the bias and provide human interpretable rules to assist specialists in the explanation of the given results. |
| Tasks | Decision Making |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1910.02043v1 |
| https://arxiv.org/pdf/1910.02043v1.pdf | |
| PWC | https://paperswithcode.com/paper/fair-by-design-explainable-models-for |
| Repo | |
| Framework | |
Large-scale Gastric Cancer Screening and Localization Using Multi-task Deep Neural Network
| Title | Large-scale Gastric Cancer Screening and Localization Using Multi-task Deep Neural Network |
| Authors | Hong Yu, Xiaofan Zhang, Lingjun Song, Liren Jiang, Xiaodi Huang, Wen Chen, Chenbin Zhang, Jiahui Li, Jiji Yang, Zhiqiang Hu, Qi Duan, Wanyuan Chen, Xianglei He, Jinshuang Fan, Weihai Jiang, Li Zhang, Chengmin Qiu, Minmin Gu, Weiwei Sun, Yangqiong Zhang, Guangyin Peng, Weiwei Shen, Guohui Fu |
| Abstract | Gastric cancer is one of the most common cancers, which ranks third among the leading causes of cancer death. Biopsy of gastric mucosal is a standard procedure in gastric cancer screening test. However, manual pathological inspection is labor-intensive and time-consuming. Besides, it is challenging for an automated algorithm to locate the small lesion regions in the gigapixel whole-slide image and make the decision correctly. To tackle these issues, we collected large-scale whole-slide image dataset with detailed lesion region annotation and designed a whole-slide image analyzing framework consisting of 3 networks which could not only determine the screen result but also present the suspicious areas to the pathologist for reference. Experiments demonstrated that our proposed framework achieves sensitivity of 97.05% and specificity of 92.72% in screening task and Dice coefficient of 0.8331 in segmentation task. Furthermore, we tested our best model in real-world scenario on 10, 316 whole-slide images collected from 4 medical centers. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03729v2 |
| https://arxiv.org/pdf/1910.03729v2.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-gastric-cancer-screening-and |
| Repo | |
| Framework | |
Pre-trained Contextual Embedding of Source Code
| Title | Pre-trained Contextual Embedding of Source Code |
| Authors | Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, Kensen Shi |
| Abstract | The source code of a program not only serves as a formal description of an executable task, but it also serves to communicate developer intent in a human-readable form. To facilitate this, developers use meaningful identifier names and natural-language documentation. This makes it possible to successfully apply sequence-modeling approaches, shown to be effective in natural-language processing, to source code. A major advancement in natural-language understanding has been the use of pre-trained token embeddings; BERT and other works have further shown that pre-trained contextual embeddings can be extremely powerful and can be fine-tuned effectively for a variety of downstream supervised tasks. Inspired by these developments, we present the first attempt to replicate this success on source code. We curate a massive corpus of Python programs from GitHub to pre-train a BERT model, which we call Code Understanding BERT (CuBERT). We also pre-train Word2Vec embeddings on the same dataset. We create a benchmark of five classification tasks and compare fine-tuned CuBERT against sequence models trained with and without the Word2Vec embeddings. Our results show that CuBERT outperforms the baseline methods by a margin of 2.9-22%. We also show its superiority when fine-tuned with smaller datasets, and over fewer epochs. We further evaluate CuBERT’s effectiveness on a joint classification, localization and repair task involving prediction of two pointers. |
| Tasks | |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/2001.00059v1 |
| https://arxiv.org/pdf/2001.00059v1.pdf | |
| PWC | https://paperswithcode.com/paper/pre-trained-contextual-embedding-of-source-1 |
| Repo | |
| Framework | |
Learning Latent Representations of Bank Customers With The Variational Autoencoder
| Title | Learning Latent Representations of Bank Customers With The Variational Autoencoder |
| Authors | Rogelio A Mancisidor, Michael Kampffmeyer, Kjersti Aas, Robert Jenssen |
| Abstract | Learning data representations that reflect the customers’ creditworthiness can improve marketing campaigns, customer relationship management, data and process management or the credit risk assessment in retail banks. In this research, we adopt the Variational Autoencoder (VAE), which has the ability to learn latent representations that contain useful information. We show that it is possible to steer the latent representations in the latent space of the VAE using the Weight of Evidence and forming a specific grouping of the data that reflects the customers’ creditworthiness. Our proposed method learns a latent representation of the data, which shows a well-defied clustering structure capturing the customers’ creditworthiness. These clusters are well suited for the aforementioned banks’ activities. Further, our methodology generalizes to new customers, captures high-dimensional and complex financial data, and scales to large data sets. |
| Tasks | |
| Published | 2019-03-14 |
| URL | http://arxiv.org/abs/1903.06580v1 |
| http://arxiv.org/pdf/1903.06580v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-latent-representations-of-bank |
| Repo | |
| Framework | |
Accelerated learning from recommender systems using multi-armed bandit
| Title | Accelerated learning from recommender systems using multi-armed bandit |
| Authors | Meisam Hejazinia, Kyler Eastman, Shuqin Ye, Abbas Amirabadi, Ravi Divvela |
| Abstract | Recommendation systems are a vital component of many online marketplaces, where there are often millions of items to potentially present to users who have a wide variety of wants or needs. Evaluating recommender system algorithms is a hard task, given all the inherent bias in the data, and successful companies must be able to rapidly iterate on their solution to maintain their competitive advantage. The gold standard for evaluating recommendation algorithms has been the A/B test since it is an unbiased way to estimate how well one or more algorithms compare in the real world. However, there are a number of issues with A/B testing that make it impractical to be the sole method of testing, including long lead time, and high cost of exploration. We argue that multi armed bandit (MAB) testing as a solution to these issues. We showcase how we implemented a MAB solution as an extra step between offline and online A/B testing in a production system. We present the result of our experiment and compare all the offline, MAB, and online A/B tests metrics for our use case. |
| Tasks | Recommendation Systems |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06158v1 |
| https://arxiv.org/pdf/1908.06158v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-learning-from-recommender-systems |
| Repo | |
| Framework | |
Data-Driven Crowd Simulation with Generative Adversarial Networks
| Title | Data-Driven Crowd Simulation with Generative Adversarial Networks |
| Authors | Javad Amirian, Wouter van Toll, Jean-Bernard Hayet, Julien Pettré |
| Abstract | This paper presents a novel data-driven crowd simulation method that can mimic the observed traffic of pedestrians in a given environment. Given a set of observed trajectories, we use a recent form of neural networks, Generative Adversarial Networks (GANs), to learn the properties of this set and generate new trajectories with similar properties. We define a way for simulated pedestrians (agents) to follow such a trajectory while handling local collision avoidance. As such, the system can generate a crowd that behaves similarly to observations, while still enabling real-time interactions between agents. Via experiments with real-world data, we show that our simulated trajectories preserve the statistical properties of their input. Our method simulates crowds in real time that resemble existing crowds, while also allowing insertion of extra agents, combination with other simulation methods, and user interaction. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09661v1 |
| https://arxiv.org/pdf/1905.09661v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-crowd-simulation-with-generative |
| Repo | |
| Framework | |
AMS-SFE: Towards an Alignment of Manifold Structures via Semantic Feature Expansion for Zero-shot Learning
| Title | AMS-SFE: Towards an Alignment of Manifold Structures via Semantic Feature Expansion for Zero-shot Learning |
| Authors | Jingcai Guo, Song Guo |
| Abstract | Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space (FS) shared by both seen and unseen classes, i.e., attributes or word vectors, as the bridge. However, due to the mutually disjoint of training (seen) and testing (unseen) data, existing ZSL methods easily and commonly suffer from the domain shift problem. To address this issue, we propose a novel model called AMS-SFE. It considers the Alignment of Manifold Structures by Semantic Feature Expansion. Specifically, we build up an autoencoder based model to expand the semantic features and joint with an alignment to an embedded manifold extracted from the visual FS of data. It is the first attempt to align these two FSs by way of expanding semantic features. Extensive experiments show the remarkable performance improvement of our model compared with other existing methods. |
| Tasks | Zero-Shot Learning |
| Published | 2019-04-12 |
| URL | http://arxiv.org/abs/1904.06254v1 |
| http://arxiv.org/pdf/1904.06254v1.pdf | |
| PWC | https://paperswithcode.com/paper/ams-sfe-towards-an-alignment-of-manifold |
| Repo | |
| Framework | |
A model of brain morphological changes related to aging and Alzheimer’s disease from cross-sectional assessments
| Title | A model of brain morphological changes related to aging and Alzheimer’s disease from cross-sectional assessments |
| Authors | Raphaël Sivera, Hervé Delingette, Marco Lorenzi, Xavier Pennec, Nicholas Ayache |
| Abstract | In this study we propose a deformation-based framework to jointly model the influence of aging and Alzheimer’s disease (AD) on the brain morphological evolution. Our approach combines a spatio-temporal description of both processes into a generative model. A reference morphology is deformed along specific trajectories to match subject specific morphologies. It is used to define two imaging progression markers: 1) a morphological age and 2) a disease score. These markers can be computed locally in any brain region. The approach is evaluated on brain structural magnetic resonance images (MRI) from the ADNI database. The generative model is first estimated on a control population, then, for each subject, the markers are computed for each acquisition. The longitudinal evolution of these markers is then studied in relation with the clinical diagnosis of the subjects and used to generate possible morphological evolution. In the model, the morphological changes associated with normal aging are mainly found around the ventricles, while the Alzheimer’s disease specific changes are more located in the temporal lobe and the hippocampal area. The statistical analysis of these markers highlights differences between clinical conditions even though the inter-subject variability is quiet high. In this context, the model can be used to generate plausible morphological trajectories associated with the disease. Our method gives two interpretable scalar imaging biomarkers assessing the effects of aging and disease on brain morphology at the individual and population level. These markers confirm an acceleration of apparent aging for Alzheimer’s subjects and can help discriminate clinical conditions even in prodromal stages. More generally, the joint modeling of normal and pathological evolutions shows promising results to describe age-related brain diseases over long time scales. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09826v1 |
| https://arxiv.org/pdf/1905.09826v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-model-of-brain-morphological-changes |
| Repo | |
| Framework | |
Soft Marginal TransE for Scholarly Knowledge Graph Completion
| Title | Soft Marginal TransE for Scholarly Knowledge Graph Completion |
| Authors | Mojtaba Nayyeri, Sahar Vahdati, Jens Lehmann, Hamed Shariat Yazdi |
| Abstract | Knowledge graphs (KGs), i.e. representation of information as a semantic graph, provide a significant test bed for many tasks including question answering, recommendation, and link prediction. Various amount of scholarly metadata have been made vailable as knowledge graphs from the diversity of data providers and agents. However, these high-quantities of data remain far from quality criteria in terms of completeness while growing at a rapid pace. Most of the attempts in completing such KGs are following traditional data digitization, harvesting and collaborative curation approaches. Whereas, advanced AI-related approaches such as embedding models - specifically designed for such tasks - are usually evaluated for standard benchmarks such as Freebase and Wordnet. The tailored nature of such datasets prevents those approaches to shed the lights on more accurate discoveries. Application of such models on domain-specific KGs takes advantage of enriched meta-data and provides accurate results where the underlying domain can enormously benefit. In this work, the TransE embedding model is reconciled for a specific link prediction task on scholarly metadata. The results show a significant shift in the accuracy and performance evaluation of the model on a dataset with scholarly metadata. The newly proposed version of TransE obtains 99.9% for link prediction task while original TransE gets 95%. In terms of accuracy and Hit@10, TransE outperforms other embedding models such as ComplEx, TransH and TransR experimented over scholarly knowledge graphs |
| Tasks | Knowledge Graph Completion, Knowledge Graphs, Link Prediction, Question Answering |
| Published | 2019-04-27 |
| URL | http://arxiv.org/abs/1904.12211v1 |
| http://arxiv.org/pdf/1904.12211v1.pdf | |
| PWC | https://paperswithcode.com/paper/soft-marginal-transe-for-scholarly-knowledge |
| Repo | |
| Framework | |
Lifelong Learning with a Changing Action Set
| Title | Lifelong Learning with a Changing Action Set |
| Authors | Yash Chandak, Georgios Theocharous, Chris Nota, Philip S. Thomas |
| Abstract | In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set changes remains unaddressed. In this paper, we present an algorithm that autonomously adapts to an action set whose size changes over time. To tackle this open problem, we break it into two problems that can be solved iteratively: inferring the underlying, unknown, structure in the space of actions and optimizing a policy that leverages this structure. We demonstrate the efficiency of this approach on large-scale real-world lifelong learning problems. |
| Tasks | Decision Making |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.01770v2 |
| https://arxiv.org/pdf/1906.01770v2.pdf | |
| PWC | https://paperswithcode.com/paper/lifelong-learning-with-a-changing-action-set |
| Repo | |
| Framework | |
