Paper Group ANR 391
New Methods of Studying Valley Fitness Landscapes. Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation. Controversy Rules - Discovering Regions Where Classifiers (Dis-)Agree Exceptionally. Finding Original Image Of A Sub Image Using CNNs. A Reinforcement Learning Approach to Age of Information in Multi …
New Methods of Studying Valley Fitness Landscapes
| Title | New Methods of Studying Valley Fitness Landscapes |
| Authors | Jun He, Tao Xu |
| Abstract | The word “valley” is a popular term used in intuitively describing fitness landscapes. What is a valley on a fitness landscape? How to identify the direction and location of a valley if it exists? However, such questions are seldom rigorously studied in evolutionary optimization especially when the search space is a high dimensional continuous space. This paper presents two methods of studying valleys on a fitness landscape. The first method is based on the topological homeomorphism. It establishes a rigorous definition of a valley. A valley is regarded as a one-dimensional manifold. The second method takes a different viewpoint from statistics. It provides an algorithm of identifying the valley direction and location using principle component analysis. |
| Tasks | |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1805.00092v1 |
| http://arxiv.org/pdf/1805.00092v1.pdf | |
| PWC | https://paperswithcode.com/paper/new-methods-of-studying-valley-fitness |
| Repo | |
| Framework | |
Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation
| Title | Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation |
| Authors | Fan Wang, Bo Zhou, Ke Chen, Tingxiang Fan, Xi Zhang, Jiangyong Li, Hao Tian, Jia Pan |
| Abstract | Combining deep neural networks with reinforcement learning has shown great potential in the next-generation intelligent control. However, there are challenges in terms of safety and cost in practical applications. In this paper, we propose the Intervention Aided Reinforcement Learning (IARL) framework, which utilizes human intervened robot-environment interaction to improve the policy. We used the Unmanned Aerial Vehicle (UAV) as the test platform. We built neural networks as our policy to map sensor readings to control signals on the UAV. Our experiment scenarios cover both simulation and reality. We show that our approach substantially reduces the human intervention and improves the performance in autonomous navigation, at the same time it ensures safety and keeps training cost acceptable. |
| Tasks | Autonomous Navigation |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06187v1 |
| http://arxiv.org/pdf/1811.06187v1.pdf | |
| PWC | https://paperswithcode.com/paper/intervention-aided-reinforcement-learning-for |
| Repo | |
| Framework | |
Controversy Rules - Discovering Regions Where Classifiers (Dis-)Agree Exceptionally
| Title | Controversy Rules - Discovering Regions Where Classifiers (Dis-)Agree Exceptionally |
| Authors | Oren Zeev-Ben-Mordehai, Wouter Duivesteijn, Mykola Pechenizkiy |
| Abstract | Finding regions for which there is higher controversy among different classifiers is insightful with regards to the domain and our models. Such evaluation can falsify assumptions, assert some, or also, bring to the attention unknown phenomena. The present work describes an algorithm, which is based on the Exceptional Model Mining framework, and enables that kind of investigations. We explore several public datasets and show the usefulness of this approach in classification tasks. We show in this paper a few interesting observations about those well explored datasets, some of which are general knowledge, and other that as far as we know, were not reported before. |
| Tasks | |
| Published | 2018-08-22 |
| URL | http://arxiv.org/abs/1808.07243v1 |
| http://arxiv.org/pdf/1808.07243v1.pdf | |
| PWC | https://paperswithcode.com/paper/controversy-rules-discovering-regions-where |
| Repo | |
| Framework | |
Finding Original Image Of A Sub Image Using CNNs
| Title | Finding Original Image Of A Sub Image Using CNNs |
| Authors | Raja Asim |
| Abstract | Convolututional Neural Networks have achieved state of the art in image classification, object detection and other image related tasks. In this paper I present another use of CNNs i.e. if given a set of images and then giving a single test image the network identifies that the test image is part of which image from the images given before. This is a task somehow similar to measuring image similarity and can be done using a simple CNN. Doing this task manually by looping can be quite a time consuming problem and won’t be a generalizable solution. The task is quite similar to doing object detection but for that lots training data should be given or in the case of sliding window it takes lot of time and my algorithm can work with much fewer examples, is totally unsupervised and works much efficiently. Also, I explain that how unsupervised algorithm like K-Means or supervised algorithm like K-NN are not good enough to perform this task. The basic idea is that image encodings are collected for each image from a CNN, when a test image comes it is replaced by a part of original image, the encoding is generated using the same network, the frobenius norm is calculated and if it comes under a tolerance level then the test image is said to be the part of the original image. |
| Tasks | Image Classification, Object Detection |
| Published | 2018-06-21 |
| URL | http://arxiv.org/abs/1806.08078v1 |
| http://arxiv.org/pdf/1806.08078v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-original-image-of-a-sub-image-using |
| Repo | |
| Framework | |
A Reinforcement Learning Approach to Age of Information in Multi-User Networks
| Title | A Reinforcement Learning Approach to Age of Information in Multi-User Networks |
| Authors | Elif Tuğçe Ceran, Deniz Gündüz, András György |
| Abstract | Scheduling the transmission of time-sensitive data to multiple users over error-prone communication channels is studied with the goal of minimizing the long-term average age of information (AoI) at the users under a constraint on the average number of transmissions at the source node. After each transmission, the source receives an instantaneous ACK/NACK feedback from the intended receiver and decides on what time and to which user to transmit the next update. The optimal scheduling policy is first studied under different feedback mechanisms when the channel statistics are known; in particular, the standard automatic repeat request (ARQ) and hybrid ARQ (HARQ) protocols are considered. Then a reinforcement learning (RL) approach is introduced, which does not assume any a priori information on the random processes governing the channel states. Different RL methods are verified and compared through numerical simulations. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00336v1 |
| http://arxiv.org/pdf/1806.00336v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-reinforcement-learning-approach-to-age-of |
| Repo | |
| Framework | |
Analogy Search Engine: Finding Analogies in Cross-Domain Research Papers
| Title | Analogy Search Engine: Finding Analogies in Cross-Domain Research Papers |
| Authors | Jieli Zhou, Yuntao Zhou, Yi Xu |
| Abstract | In recent years, with the rapid proliferation of research publications in the field of Artificial Intelligence, it is becoming increasingly difficult for researchers to effectively keep up with all the latest research in one’s own domains. However, history has shown that scientific breakthroughs often come from collaborations of researchers from different domains. Traditional search algorithms like Lexical search, which look for literal matches or synonyms and variants of the query words, are not effective for discovering cross-domain research papers and meeting the needs of researchers in this age of information overflow. In this paper, we developed and tested an innovative semantic search engine, Analogy Search Engine (ASE), for 2000 AI research paper abstracts across domains like Language Technologies, Robotics, Machine Learning, Computational Biology, Human Computer Interactions, etc. ASE combines recent theories and methods from Computational Analogy and Natural Language Processing to go beyond keyword-based lexical search and discover the deeper analogical relationships among research paper abstracts. We experimentally show that ASE is capable of finding more interesting and useful research papers than baseline elasticsearch. Furthermore, we believe that the methods used in ASE go beyond academic paper and will benefit many other document search tasks. |
| Tasks | |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.06974v1 |
| http://arxiv.org/pdf/1812.06974v1.pdf | |
| PWC | https://paperswithcode.com/paper/analogy-search-engine-finding-analogies-in |
| Repo | |
| Framework | |
From FiLM to Video: Multi-turn Question Answering with Multi-modal Context
| Title | From FiLM to Video: Multi-turn Question Answering with Multi-modal Context |
| Authors | Dat Tien Nguyen, Shikhar Sharma, Hannes Schulz, Layla El Asri |
| Abstract | Understanding audio-visual content and the ability to have an informative conversation about it have both been challenging areas for intelligent systems. The Audio Visual Scene-aware Dialog (AVSD) challenge, organized as a track of the Dialog System Technology Challenge 7 (DSTC7), proposes a combined task, where a system has to answer questions pertaining to a video given a dialogue with previous question-answer pairs and the video itself. We propose for this task a hierarchical encoder-decoder model which computes a multi-modal embedding of the dialogue context. It first embeds the dialogue history using two LSTMs. We extract video and audio frames at regular intervals and compute semantic features using pre-trained I3D and VGGish models, respectively. Before summarizing both modalities into fixed-length vectors using LSTMs, we use FiLM blocks to condition them on the embeddings of the current question, which allows us to reduce the dimensionality considerably. Finally, we use an LSTM decoder that we train with scheduled sampling and evaluate using beam search. Compared to the modality-fusing baseline model released by the AVSD challenge organizers, our model achieves a relative improvements of more than 16%, scoring 0.36 BLEU-4 and more than 33%, scoring 0.997 CIDEr. |
| Tasks | Question Answering |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.07023v1 |
| http://arxiv.org/pdf/1812.07023v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-film-to-video-multi-turn-question |
| Repo | |
| Framework | |
Linking ImageNet WordNet Synsets with Wikidata
| Title | Linking ImageNet WordNet Synsets with Wikidata |
| Authors | Finn Årup Nielsen |
| Abstract | The linkage of ImageNet WordNet synsets to Wikidata items will leverage deep learning algorithm with access to a rich multilingual knowledge graph. Here I will describe our on-going efforts in linking the two resources and issues faced in matching the Wikidata and WordNet knowledge graphs. I show an example on how the linkage can be used in a deep learning setting with real-time image classification and labeling in a non-English language and discuss what opportunities lies ahead. |
| Tasks | Image Classification, Knowledge Graphs |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.04349v1 |
| http://arxiv.org/pdf/1803.04349v1.pdf | |
| PWC | https://paperswithcode.com/paper/linking-imagenet-wordnet-synsets-with |
| Repo | |
| Framework | |
The Role of Information Complexity and Randomization in Representation Learning
| Title | The Role of Information Complexity and Randomization in Representation Learning |
| Authors | Matías Vera, Pablo Piantanida, Leonardo Rey Vega |
| Abstract | A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective is to generalize well to unseen data. Although there is enough numerical evidence suggesting that noise injection (during training) at the representation level might improve the generalization ability of encoders, an information-theoretic understanding of this principle remains elusive. This paper presents a sample-dependent bound on the generalization gap of the cross-entropy loss that scales with the information complexity (IC) of the representations, meaning the mutual information between inputs and their representations. The IC is empirically investigated for standard multi-layer neural networks with SGD on MNIST and CIFAR-10 datasets; the behaviour of the gap and the IC appear to be in direct correlation, suggesting that SGD selects encoders to implicitly minimize the IC. We specialize the IC to study the role of Dropout on the generalization capacity of deep encoders which is shown to be directly related to the encoder capacity, being a measure of the distinguishability among samples from their representations. Our results support some recent regularization methods. |
| Tasks | Representation Learning |
| Published | 2018-02-14 |
| URL | http://arxiv.org/abs/1802.05355v1 |
| http://arxiv.org/pdf/1802.05355v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-role-of-information-complexity-and |
| Repo | |
| Framework | |
Learning Optimal Personalized Treatment Rules Using Robust Regression Informed K-NN
| Title | Learning Optimal Personalized Treatment Rules Using Robust Regression Informed K-NN |
| Authors | Ruidi Chen, Ioannis Paschalidis |
| Abstract | We develop a prediction-based prescriptive model for learning optimal personalized treatments for patients based on their Electronic Health Records (EHRs). Our approach consists of: (i) predicting future outcomes under each possible therapy using a robustified nonlinear model, and (ii) adopting a randomized prescriptive policy determined by the predicted outcomes. We show theoretical results that guarantee the out-of-sample predictive power of the model, and prove the optimality of the randomized strategy in terms of the expected true future outcome. We apply the proposed methodology to develop optimal therapies for patients with type 2 diabetes or hypertension using EHRs from a major safety-net hospital in New England, and show that our algorithm leads to a larger reduction of the HbA1c, for diabetics, or systolic blood pressure, for patients with hypertension, compared to the alternatives. We demonstrate that our approach outperforms the standard of care under the robustified nonlinear predictive model. |
| Tasks | |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.06083v3 |
| http://arxiv.org/pdf/1811.06083v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-optimal-personalized-treatment-rules |
| Repo | |
| Framework | |
Explaining Latent Factor Models for Recommendation with Influence Functions
| Title | Explaining Latent Factor Models for Recommendation with Influence Functions |
| Authors | Weiyu Cheng, Yanyan Shen, Yanmin Zhu, Linpeng Huang |
| Abstract | Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue to be resolved is the lack of explainability. Extensive efforts have been made in the literature to incorporate explainability into LFMs. However, they either rely on auxiliary information which may not be available in practice, or fail to provide easy-to-understand explanations. In this paper, we propose a fast influence analysis method named FIA, which successfully enforces explicit neighbor-style explanations to LFMs with the technique of influence functions stemmed from robust statistics. We first describe how to employ influence functions to LFMs to deliver neighbor-style explanations. Then we develop a novel influence computation algorithm for matrix factorization with high efficiency. We further extend it to the more general neural collaborative filtering and introduce an approximation algorithm to accelerate influence analysis over neural network models. Experimental results on real datasets demonstrate the correctness, efficiency and usefulness of our proposed method. |
| Tasks | |
| Published | 2018-11-20 |
| URL | http://arxiv.org/abs/1811.08120v1 |
| http://arxiv.org/pdf/1811.08120v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-latent-factor-models-for |
| Repo | |
| Framework | |
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
| Title | Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes |
| Authors | Roman Novak, Lechao Xiao, Jaehoon Lee, Yasaman Bahri, Greg Yang, Jiri Hron, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein |
| Abstract | There is a previously identified equivalence between wide fully connected neural networks (FCNs) and Gaussian processes (GPs). This equivalence enables, for instance, test set predictions that would have resulted from a fully Bayesian, infinitely wide trained FCN to be computed without ever instantiating the FCN, but by instead evaluating the corresponding GP. In this work, we derive an analogous equivalence for multi-layer convolutional neural networks (CNNs) both with and without pooling layers, and achieve state of the art results on CIFAR10 for GPs without trainable kernels. We also introduce a Monte Carlo method to estimate the GP corresponding to a given neural network architecture, even in cases where the analytic form has too many terms to be computationally feasible. Surprisingly, in the absence of pooling layers, the GPs corresponding to CNNs with and without weight sharing are identical. As a consequence, translation equivariance, beneficial in finite channel CNNs trained with stochastic gradient descent (SGD), is guaranteed to play no role in the Bayesian treatment of the infinite channel limit - a qualitative difference between the two regimes that is not present in the FCN case. We confirm experimentally, that while in some scenarios the performance of SGD-trained finite CNNs approaches that of the corresponding GPs as the channel count increases, with careful tuning SGD-trained CNNs can significantly outperform their corresponding GPs, suggesting advantages from SGD training compared to fully Bayesian parameter estimation. |
| Tasks | Gaussian Processes |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.05148v3 |
| http://arxiv.org/pdf/1810.05148v3.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-deep-convolutional-networks-with |
| Repo | |
| Framework | |
Adapting Neural Text Classification for Improved Software Categorization
| Title | Adapting Neural Text Classification for Improved Software Categorization |
| Authors | Alexander LeClair, Zachary Eberhart, Collin McMillan |
| Abstract | Software Categorization is the task of organizing software into groups that broadly describe the behavior of the software, such as “editors” or “science.” Categorization plays an important role in several maintenance tasks, such as repository navigation and feature elicitation. Current approaches attempt to cast the problem as text classification, to make use of the rich body of literature from the NLP domain. However, as we will show in this paper, text classification algorithms are generally not applicable off-the-shelf to source code; we found that they work well when high-level project descriptions are available, but suffer very large performance penalties when classifying source code and comments only. We propose a set of adaptations to a state-of-the-art neural classification algorithm and perform two evaluations: one with reference data from Debian end-user programs, and one with a set of C/C++ libraries that we hired professional programmers to annotate. We show that our proposed approach achieves performance exceeding that of previous software classification techniques as well as a state-of-the-art neural text classification technique. |
| Tasks | Text Classification |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01742v2 |
| http://arxiv.org/pdf/1806.01742v2.pdf | |
| PWC | https://paperswithcode.com/paper/adapting-neural-text-classification-for |
| Repo | |
| Framework | |
Reliable Intersection Control in Non-cooperative Environments
| Title | Reliable Intersection Control in Non-cooperative Environments |
| Authors | Muhammed O. Sayin, Chung-Wei Lin, Shinichi Shiraishi, Tamer Başar |
| Abstract | We propose a reliable intersection control mechanism for strategic autonomous and connected vehicles (agents) in non-cooperative environments. Each agent has access to his/her earliest possible and desired passing times, and reports a passing time to the intersection manager, who allocates the intersection temporally to the agents in a First-Come-First-Serve basis. However, the agents might have conflicting interests and can take actions strategically. To this end, we analyze the strategic behaviors of the agents and formulate Nash equilibria for all possible scenarios. Furthermore, among all Nash equilibria we identify a socially optimal equilibrium that leads to a fair intersection allocation, and correspondingly we describe a strategy-proof intersection mechanism, which achieves reliable intersection control such that the strategic agents do not have any incentive to misreport their passing times strategically. |
| Tasks | |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08138v1 |
| http://arxiv.org/pdf/1802.08138v1.pdf | |
| PWC | https://paperswithcode.com/paper/reliable-intersection-control-in-non |
| Repo | |
| Framework | |
The Vadalog System: Datalog-based Reasoning for Knowledge Graphs
| Title | The Vadalog System: Datalog-based Reasoning for Knowledge Graphs |
| Authors | Luigi Bellomarini, Georg Gottlob, Emanuel Sallinger |
| Abstract | Over the past years, there has been a resurgence of Datalog-based systems in the database community as well as in industry. In this context, it has been recognized that to handle the complex knowl-edge-based scenarios encountered today, such as reasoning over large knowledge graphs, Datalog has to be extended with features such as existential quantification. Yet, Datalog-based reasoning in the presence of existential quantification is in general undecidable. Many efforts have been made to define decidable fragments. Warded Datalog+/- is a very promising one, as it captures PTIME complexity while allowing ontological reasoning. Yet so far, no implementation of Warded Datalog+/- was available. In this paper we present the Vadalog system, a Datalog-based system for performing complex logic reasoning tasks, such as those required in advanced knowledge graphs. The Vadalog system is Oxford’s contribution to the VADA research programme, a joint effort of the universities of Oxford, Manchester and Edinburgh and around 20 industrial partners. As the main contribution of this paper, we illustrate the first implementation of Warded Datalog+/-, a high-performance Datalog+/- system utilizing an aggressive termination control strategy. We also provide a comprehensive experimental evaluation. |
| Tasks | Knowledge Graphs |
| Published | 2018-07-23 |
| URL | http://arxiv.org/abs/1807.08709v1 |
| http://arxiv.org/pdf/1807.08709v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-vadalog-system-datalog-based-reasoning |
| Repo | |
| Framework | |
