Paper Group ANR 1097
Reasoning Over Paragraph Effects in Situations. Characterization and Development of Average Silhouette Width Clustering. An Extensible and Personalizable Multi-Modal Trip Planner. On the Adversarial Robustness of Subspace Learning. Fair quantile regression. Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Chan …
Reasoning Over Paragraph Effects in Situations
| Title | Reasoning Over Paragraph Effects in Situations |
| Authors | Kevin Lin, Oyvind Tafjord, Peter Clark, Matt Gardner |
| Abstract | A key component of successfully reading a passage of text is the ability to apply knowledge gained from the passage to a new situation. In order to facilitate progress on this kind of reading, we present ROPES, a challenging benchmark for reading comprehension targeting Reasoning Over Paragraph Effects in Situations. We target expository language describing causes and effects (e.g., “animal pollinators increase efficiency of fertilization in flowers”), as they have clear implications for new situations. A system is presented a background passage containing at least one of these relations, a novel situation that uses this background, and questions that require reasoning about effects of the relationships in the background passage in the context of the situation. We collect background passages from science textbooks and Wikipedia that contain such phenomena, and ask crowd workers to author situations, questions, and answers, resulting in a 14,322 question dataset. We analyze the challenges of this task and evaluate the performance of state-of-the-art reading comprehension models. The best model performs only slightly better than randomly guessing an answer of the correct type, at 61.6% F1, well below the human performance of 89.0%. |
| Tasks | Reading Comprehension |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05852v2 |
| https://arxiv.org/pdf/1908.05852v2.pdf | |
| PWC | https://paperswithcode.com/paper/reasoning-over-paragraph-effects-in |
| Repo | |
| Framework | |
Characterization and Development of Average Silhouette Width Clustering
| Title | Characterization and Development of Average Silhouette Width Clustering |
| Authors | Fatima Batool, Christian Hennig |
| Abstract | The purpose of this paper is to introduced a new clustering methodology. This paper is divided into three parts. In the first part we have developed the axiomatic theory for the average silhouette width (ASW) index. There are different ways to investigate the quality and characteristics of clustering methods such as validation indices using simulations and real data experiments, model-based theory, and non-model-based theory known as the axiomatic theory. In this work we have not only taken the empirical approach of validation of clustering results through simulations, but also focus on the development of the axiomatic theory. In the second part we have presented a novel clustering methodology based on the optimization of the ASW index. We have considered the problem of estimation of number of clusters and finding clustering against this number simultaneously. Two algorithms are proposed. The proposed algorithms are evaluated against several partitioning and hierarchical clustering methods. An intensive empirical comparison of the different distance metrics on the various clustering methods is conducted. In the third part we have considered two application domains\textemdash novel single cell RNA sequencing datasets and rainfall data to cluster weather stations. |
| Tasks | |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11339v1 |
| https://arxiv.org/pdf/1910.11339v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterization-and-development-of-average |
| Repo | |
| Framework | |
An Extensible and Personalizable Multi-Modal Trip Planner
| Title | An Extensible and Personalizable Multi-Modal Trip Planner |
| Authors | Xudong Liu, Christian Fritz, Matthew Klenk |
| Abstract | Despite a tremendous amount of work in the literature and in the commercial sectors, current approaches to multi-modal trip planning still fail to consistently generate plans that users deem optimal in practice. We believe that this is due to the fact that current planners fail to capture the true preferences of users, e.g., their preferences depend on aspects that are not modeled. An example of this could be a preference not to walk through an unsafe area at night. We present a novel multi-modal trip planner that allows users to upload auxiliary geographic data (e.g., crime rates) and to specify temporal constraints and preferences over these data in combination with typical metrics such as time and cost. Concretely, our planner supports the modes walking, biking, driving, public transit, and taxi, uses linear temporal logic to capture temporal constraints, and preferential cost functions to represent preferences. We show by examples that this allows the expression of very interesting preferences and constraints that, naturally, lead to quite diverse optimal plans. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11604v1 |
| https://arxiv.org/pdf/1909.11604v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-extensible-and-personalizable-multi-modal |
| Repo | |
| Framework | |
On the Adversarial Robustness of Subspace Learning
| Title | On the Adversarial Robustness of Subspace Learning |
| Authors | Fuwei Li, Lifeng Lai, Shuguang Cui |
| Abstract | In this paper, we study the adversarial robustness of subspace learning problems. Different from the assumptions made in existing work on robust subspace learning where data samples are contaminated by gross sparse outliers or small dense noises, we consider a more powerful adversary who can first observe the data matrix and then intentionally modify the whole data matrix. We first characterize the optimal rank-one attack strategy that maximizes the subspace distance between the subspace learned from the original data matrix and that learned from the modified data matrix. We then generalize the study to the scenario without the rank constraint and characterize the corresponding optimal attack strategy. Our analysis shows that the optimal strategies depend on the singular values of the original data matrix and the adversary’s energy budget. Finally, we provide numerical experiments and practical applications to demonstrate the efficiency of the attack strategies. |
| Tasks | |
| Published | 2019-08-17 |
| URL | https://arxiv.org/abs/1908.06210v1 |
| https://arxiv.org/pdf/1908.06210v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-adversarial-robustness-of-subspace |
| Repo | |
| Framework | |
Fair quantile regression
| Title | Fair quantile regression |
| Authors | Dana Yang, John Lafferty, David Pollard |
| Abstract | Quantile regression is a tool for learning conditional distributions. In this paper we study quantile regression in the setting where a protected attribute is unavailable when fitting the model. This can lead to “unfair’’ quantile estimators for which the effective quantiles are very different for the subpopulations defined by the protected attribute. We propose a procedure for adjusting the estimator on a heldout sample where the protected attribute is available. The main result of the paper is an empirical process analysis showing that the adjustment leads to a fair estimator for which the target quantiles are brought into balance, in a statistical sense that we call $\sqrt{n}$-fairness. We illustrate the ideas and adjustment procedure on a dataset of 200,000 live births, where the objective is to characterize the dependence of the birth weights of the babies on demographic attributes of the birth mother; the protected attribute is the mother’s race. |
| Tasks | |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08646v1 |
| https://arxiv.org/pdf/1907.08646v1.pdf | |
| PWC | https://paperswithcode.com/paper/fair-quantile-regression |
| Repo | |
| Framework | |
Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands
| Title | Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands |
| Authors | Minho Park, Hak Gu Kim, Yong Man Ro |
| Abstract | Realistic image synthesis is to generate an image that is perceptually indistinguishable from an actual image. Generating realistic looking images with large variations (e.g., large spatial deformations and large pose change), however, is very challenging. Handing large variations as well as preserving appearance needs to be taken into account in the realistic looking image generation. In this paper, we propose a novel realistic looking image synthesis method, especially in large change demands. To do that, we devise generative guiding blocks. The proposed generative guiding block includes realistic appearance preserving discriminator and naturalistic variation transforming discriminator. By taking the proposed generative guiding blocks into generative model, the latent features at the layer of generative model are enhanced to synthesize both realistic looking- and target variation- image. With qualitative and quantitative evaluation in experiments, we demonstrated the effectiveness of the proposed generative guiding blocks, compared to the state-of-the-arts. |
| Tasks | Image Generation |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01187v1 |
| https://arxiv.org/pdf/1907.01187v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-guiding-block-synthesizing |
| Repo | |
| Framework | |
Reinforcement Learning for Optimal Load Distribution Sequencing in Resource-Sharing System
| Title | Reinforcement Learning for Optimal Load Distribution Sequencing in Resource-Sharing System |
| Authors | Fei Wu, Yang Cao, Thomas Robertazzi |
| Abstract | Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems. This paper studied an optimal divisible load distribution sequencing problem using a machine learning framework. The problem is to decide the optimal sequence to distribute divisible load to processors in order to achieve minimum finishing time. The scheduling is performed in a resource-sharing system where each physical processor is virtualized to multiple virtual processors. A reinforcement learning method called Multi-armed bandit (MAB) is used for our problem. We first provide a naive solution using the MAB algorithm and then several optimizations are performed. Various numerical tests are conducted. Our algorithm shows an increasing performance during the training progress and the global optimum will be acheived when the sample size is large enough. |
| Tasks | |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01899v1 |
| http://arxiv.org/pdf/1902.01899v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-for-optimal-load |
| Repo | |
| Framework | |
Estimating a Manifold from a Tangent Bundle Learner
| Title | Estimating a Manifold from a Tangent Bundle Learner |
| Authors | Bharathkumar Ramachandra, Benjamin Dutton, Ranga Raju Vatsavai |
| Abstract | Manifold hypotheses are typically used for tasks such as dimensionality reduction, interpolation, or improving classification performance. In the less common problem of manifold estimation, the task is to characterize the geometric structure of the manifold in the original ambient space from a sample. We focus on the role that tangent bundle learners (TBL) can play in estimating the underlying manifold from which data is assumed to be sampled. Since the unbounded tangent spaces natively represent a poor manifold estimate, the problem reduces to one of estimating regions in the tangent space where it acts as a relatively faithful linear approximator to the surface of the manifold. Local PCA methods, such as the Mixtures of Probabilistic Principal Component Analyzers method of Tipping and Bishop produce a subset of the tangent bundle of the manifold along with an assignment function that assigns points in the training data used by the TBL to elements of the estimated tangent bundle. We formulate three methods that use the data assigned to each tangent space to estimate the underlying bounded subspaces for which the tangent space is a faithful estimate of the manifold and offer thoughts on how this perspective is theoretically grounded in the manifold assumption. We seek to explore the conceptual and technical challenges that arise in trying to utilize simple TBL methods to arrive at reliable estimates of the underlying manifold. |
| Tasks | Dimensionality Reduction |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07661v1 |
| https://arxiv.org/pdf/1906.07661v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-a-manifold-from-a-tangent-bundle |
| Repo | |
| Framework | |
Beyond Turing: Intelligent Agents Centered on the User
| Title | Beyond Turing: Intelligent Agents Centered on the User |
| Authors | Maxine Eskenazi, Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao |
| Abstract | Most research on intelligent agents centers on the agent and not on the user. We look at the origins of agent-centric research for slot-filling, gaming and chatbot agents. We then argue that it is important to concentrate more on the user. After reviewing relevant literature, some approaches for creating and assessing user-centric systems are proposed. |
| Tasks | Chatbot, Slot Filling |
| Published | 2019-01-20 |
| URL | http://arxiv.org/abs/1901.06613v2 |
| http://arxiv.org/pdf/1901.06613v2.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-turing-intelligent-agents-centered-on |
| Repo | |
| Framework | |
Fast Transformer Decoding: One Write-Head is All You Need
| Title | Fast Transformer Decoding: One Write-Head is All You Need |
| Authors | Noam Shazeer |
| Abstract | Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to parallelizability across the length of the sequence, incremental inference (where such paralleization is impossible) is often slow, due to the memory-bandwidth cost of repeatedly loading the large “keys” and “values” tensors. We propose a variant called multi-query attention, where the keys and values are shared across all of the different attention “heads”, greatly reducing the size of these tensors and hence the memory bandwidth requirements of incremental decoding. We verify experimentally that the resulting models can indeed be much faster to decode, and incur only minor quality degradation from the baseline. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02150v1 |
| https://arxiv.org/pdf/1911.02150v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-transformer-decoding-one-write-head-is |
| Repo | |
| Framework | |
Bayesian Anomaly Detection Using Extreme Value Theory
| Title | Bayesian Anomaly Detection Using Extreme Value Theory |
| Authors | Sreelekha Guggilam, S. M. Arshad Zaidi, Varun Chandola, Abani Patra |
| Abstract | Data-driven anomaly detection methods typically build a model for the normal behavior of the target system, and score each data instance with respect to this model. A threshold is invariably needed to identify data instances with high (or low) scores as anomalies. This presents a practical limitation on the applicability of such methods, since most methods are sensitive to the choice of the threshold, and it is challenging to set optimal thresholds. We present a probabilistic framework to explicitly model the normal and anomalous behaviors and probabilistically reason about the data. An extreme value theory based formulation is proposed to model the anomalous behavior as the extremes of the normal behavior. As a specific instantiation, a joint non-parametric clustering and anomaly detection algorithm is proposed that models the normal behavior as a Dirichlet Process Mixture Model. |
| Tasks | Anomaly Detection |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12150v2 |
| https://arxiv.org/pdf/1905.12150v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-anomaly-detection-using-extreme |
| Repo | |
| Framework | |
Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamics
| Title | Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamics |
| Authors | Grady Williams, Brian Goldfain, James M. Rehg, Evangelos A. Theodorou |
| Abstract | We consider the problem of online adaptation of a neural network designed to represent vehicle dynamics. The neural network model is intended to be used by an MPC control law to autonomously control the vehicle. This problem is challenging because both the input and target distributions are non-stationary, and naive approaches to online adaptation result in catastrophic forgetting, which can in turn lead to controller failures. We present a novel online learning method, which combines the pseudo-rehearsal method with locally weighted projection regression. We demonstrate the effectiveness of the resulting Locally Weighted Projection Regression Pseudo-Rehearsal (LW-PR$^2$) method in simulation and on a large real world dataset collected with a 1/5 scale autonomous vehicle. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05162v1 |
| https://arxiv.org/pdf/1905.05162v1.pdf | |
| PWC | https://paperswithcode.com/paper/locally-weighted-regression-pseudo-rehearsal |
| Repo | |
| Framework | |
Structured Multi-Hashing for Model Compression
| Title | Structured Multi-Hashing for Model Compression |
| Authors | Elad Eban, Yair Movshovitz-Attias, Hao Wu, Mark Sandler, Andrew Poon, Yerlan Idelbayev, Miguel A. Carreira-Perpinan |
| Abstract | Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this limitation by reducing the memory footprint, latency, or energy consumption of a model with minimal impact on accuracy. We focus on the task of reducing the number of learnable variables in the model. In this work we combine ideas from weight hashing and dimensionality reductions resulting in a simple and powerful structured multi-hashing method based on matrix products that allows direct control of model size of any deep network and is trained end-to-end. We demonstrate the strength of our approach by compressing models from the ResNet, EfficientNet, and MobileNet architecture families. Our method allows us to drastically decrease the number of variables while maintaining high accuracy. For instance, by applying our approach to EfficentNet-B4 (16M parameters) we reduce it to to the size of B0 (5M parameters), while gaining over 3% in accuracy over B0 baseline. On the commonly used benchmark CIFAR10 we reduce the ResNet32 model by 75% with no loss in quality, and are able to do a 10x compression while still achieving above 90% accuracy. |
| Tasks | Model Compression |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11177v1 |
| https://arxiv.org/pdf/1911.11177v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-multi-hashing-for-model |
| Repo | |
| Framework | |
Exploring Pose Priors for Human Pose Estimation with Joint Angle Representations
| Title | Exploring Pose Priors for Human Pose Estimation with Joint Angle Representations |
| Authors | Yaadhav Raaj |
| Abstract | Pose Priors are critical in human pose estimation, since they are able to enforce constraints that prevent estimated poses from tending to physically impossible positions. Human pose generally consists of up to 22 Joint Angles of various segments, and their respective bone lengths, but the way these various segments interact can affect the validity of a pose. Looking at the Knee-Ankle segment alone, we can observe that clearly, the Knee cannot bend forward beyond it’s roughly 90 degree point, amongst various other impossible poses below. |
| Tasks | Pose Estimation |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1909.12761v1 |
| https://arxiv.org/pdf/1909.12761v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-pose-priors-for-human-pose |
| Repo | |
| Framework | |
Resolving Marker Pose Ambiguity by Robust Rotation Averaging with Clique Constraints
| Title | Resolving Marker Pose Ambiguity by Robust Rotation Averaging with Clique Constraints |
| Authors | Shin-Fang Ch’ng, Naoya Sogi, Pulak Purkait, Tat-Jun Chin, Kazuhiro Fukui |
| Abstract | Planar markers are useful in robotics and computer vision for mapping and localisation. Given a detected marker in an image, a frequent task is to estimate the 6DOF pose of the marker relative to the camera, which is an instance of planar pose estimation (PPE). Although there are mature techniques, PPE suffers from a fundamental ambiguity problem, in that there can be more than one plausible pose solutions for a PPE instance. Especially when localisation of the marker corners is noisy, it is often difficult to disambiguate the pose solutions based on reprojection error alone. Previous methods choose between the possible solutions using a heuristic criteria, or simply ignore ambiguous markers. We propose to resolve the ambiguities by examining the consistencies of a set of markers across multiple views. Our specific contributions include a novel rotation averaging formulation that incorporates long-range dependencies between possible marker orientation solutions that arise from PPE ambiguities. We analyse the combinatorial complexity of the problem, and develop a novel lifted algorithm to effectively resolve marker pose ambiguities, without discarding any marker observations. Results on real and synthetic data show that our method is able to handle highly ambiguous inputs, and provides more accurate and/or complete marker-based mapping and localisation. |
| Tasks | Pose Estimation |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.11888v1 |
| https://arxiv.org/pdf/1909.11888v1.pdf | |
| PWC | https://paperswithcode.com/paper/resolving-marker-pose-ambiguity-by-robust |
| Repo | |
| Framework | |
