今日 cs.AI方向共计19篇文章。
Artificial Intelligence(14篇)
[1]：Dung's semantics satisfy attack removal monotonicity
标题：Dung的语义满足攻击去除的单调性
作者：Leila Amgoud, Srdjan Vesic
链接：https://arxiv.org/abs/2007.04221
摘要：We show that preferred, stable, complete, and grounded semantics satisfy attack removal monotonicity. This means that if an attack from b to a is removed, the status of a cannot worsen, e.g. if a was skeptically accepted, it cannot become rejected.
[2]：Reconciling Causality and Statistics
标题：调和因果关系和统计数据
作者：Pirmin Lemberger, Denis Oblin
备注：22 pages, 14 figures
链接：https://arxiv.org/abs/2007.03940
摘要：Statisticians have warned us since the early days of their discipline that experimental correlation between two observations by no means implies the existence of a causal relation. The question about what clues exist in observational data that could informs us about the existence of such causal relations is nevertheless more that legitimate. It lies actually at the root of any scientific endeavor. For decades however the only accepted method among statisticians to elucidate causal relationships was the so called Randomized Controlled Trial. Besides this notorious exception causality questions remained largely taboo for many. One reason for this state of affairs was the lack of an appropriate mathematical framework to formulate such questions in an unambiguous way. Fortunately thinks have changed these last years with the advent of the so called Causality Revolution initiated by Judea Pearl and coworkers. The aim of this pedagogical paper is to present their ideas and methods in a compact and self-contained fashion with concrete business examples as illustrations.
[3]：Deep Reinforcement Learning and its Neuroscientific Implications
标题：深度强化学习及其神经科学意义
作者：Matthew Botvinick, Jane X. Wang, Will Dabney, Kevin J. Miller, Zeb Kurth-Nelson
备注：22 pages, 5 figures
链接：https://arxiv.org/abs/2007.03750
摘要：The emergence of powerful artificial intelligence is defining new research directions in neuroscience. To date, this research has focused largely on deep neural networks trained using supervised learning, in tasks such as image classification. However, there is another area of recent AI work which has so far received less attention from neuroscientists, but which may have profound neuroscientific implications: deep reinforcement learning. Deep RL offers a comprehensive framework for studying the interplay among learning, representation and decision-making, offering to the brain sciences a new set of research tools and a wide range of novel hypotheses. In the present review, we provide a high-level introduction to deep RL, discuss some of its initial applications to neuroscience, and survey its wider implications for research on brain and behavior, concluding with a list of opportunities for next-stage research.
[4]：TripMD: Driving patterns investigation via Motif Analysis
标题：TripMD：基于Motif分析的驾驶模式研究
作者：Maria Inê Silva, Roberto Henriques
备注：10 pages, 6 figures
链接：https://arxiv.org/abs/2007.03727
摘要：Processing driving data and investigating driving behavior has been receiving an increasing interest in the last decades, with applications ranging from car insurance pricing to policy making. A common strategy to analyze driving behavior analysis is to study the maneuvers being performance by the driver. In this paper, we propose TripMD, a system that extracts the most relevant driving patterns from sensor recordings (such as acceleration) and provides a visualization that allows for an easy investigation. Additionally, we test our system using the UAH-DriveSet dataset, a publicly available naturalistic driving dataset. We show that (1) our system can extract a rich number of driving patterns from a single driver that are meaningful to understand driving behaviors and (2) our system can be used to identify the driving behavior of an unknown driver from a set of drivers whose behavior we know.
[5]：AutoLR: An Evolutionary Approach to Learning Rate Policies
标题：AutoLR：学习速率策略的进化方法
作者：Pedro Carvalho, Nuno Lourenço, Filipe Assunção, Penousal Machado
链接：https://arxiv.org/abs/2007.04223
摘要：The choice of a proper learning rate is paramount for good Artificial Neural Network training and performance. In the past, one had to rely on experience and trial-and-error to find an adequate learning rate. Presently, a plethora of state of the art automatic methods exist that make the search for a good learning rate easier. While these techniques are effective and have yielded good results over the years, they are general solutions. This means the optimization of learning rate for specific network topologies remains largely unexplored. This work presents AutoLR, a framework that evolves Learning Rate Schedulers for a specific Neural Network Architecture using Structured Grammatical Evolution. The system was used to evolve learning rate policies that were compared with a commonly used baseline value for learning rate. Results show that training performed using certain evolved policies is more efficient than the established baseline and suggest that this approach is a viable means of improving a neural network's performance.
[6]：The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning
标题：离散组合学习者：类比推理中的对象、属性、关系的发现
作者：Yuhuai Wu, Honghua Dong, Roger Grosse, Jimmy Ba
链接：https://arxiv.org/abs/2007.04212
摘要：In this work, we focus on an analogical reasoning task that contains rich compositional structures, Raven's Progressive Matrices (RPM). To discover compositional structures of the data, we propose the Scattering Compositional Learner (SCL), an architecture that composes neural networks in a sequence. Our SCL achieves state-of-the-art performance on two RPM datasets, with a 48.7% relative improvement on Balanced-RAVEN and 26.4% on PGM over the previous state-of-the-art. We additionally show that our model discovers compositional representations of objects' attributes (e.g., shape color, size), and their relationships (e.g., progression, union). We also find that the compositional representation makes the SCL significantly more robust to test-time domain shifts and greatly improves zero-shot generalization to previously unseen analogies.
[7]：A Natural Actor-Critic Algorithm with Downside Risk Constraints
标题：一种具有下行风险约束的自然行为人批评算法
作者：Thomas Spooner, Rahul Savani
备注：14 pages, 5 figures
链接：https://arxiv.org/abs/2007.04203
摘要：Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also suffers from high variance and decreased sample efficiency compared to temporal-difference methods. In this paper, we study prediction and control with aversion to downside risk which we gauge by the lower partial moment of the return. We introduce a new Bellman equation that upper bounds the lower partial moment, circumventing its non-linearity. We prove that this proxy for the lower partial moment is a contraction, and provide intuition into the stability of the algorithm by variance decomposition. This allows sample-efficient, on-line estimation of partial moments. For risk-sensitive control, we instantiate Reward Constrained Policy Optimization, a recent actor-critic method for finding constrained policies, with our proxy for the lower partial moment. We extend the method to use natural policy gradients and demonstrate the effectiveness of our approach on three benchmark problems for risk-sensitive reinforcement learning.
[8]：An exploration of the influence of path choice in game-theoretic attribution algorithms
标题：博弈论属性算法中路径选择影响的探讨
作者：Geoff Ward, Sean Kamkar, Jay Budzik
备注：21 pages, 23 figures, submitted to JMLR 7/7/2020
链接：https://arxiv.org/abs/2007.04169
摘要：We compare machine learning explainability methods based on the theory of atomic (Shapley, 1953) and infinitesimal (Aumann and Shapley, 1974) games, in a theoretical and experimental investigation into how the model and choice of integration path can influence the resulting feature attributions. To gain insight into differences in attributions resulting from interventional Shapley values (Sundararajan and Najmi, 2019; Janzing et al., 2019; Chen et al., 2019) and Generalized Integrated Gradients (GIG) (Merrill et al., 2019) we note interventional Shapley is equivalent to a multi-path integration along $n!$ paths where $n$ is the number of model input features. Applying Stoke's theorem we show that the path symmetry of these two methods results in the same attributions when the model is composed of a sum of separable functions of individual features and a sum of two-feature products. We then perform a series of experiments with varying degrees of data missingness to demonstrate how interventional Shapley's multi-path approach can yield less consistent attributions than the single straight-line path of Aumann-Shapley. We argue this is because the multiple paths employed by interventional Shaply extend away from the training data manifold and are therefore more likely to pass through regions where the model has little support. In the absence of a more meaningful path choice, we therefore advocate the straight-line path since it will almost always pass closer to the data manifold. Among straight-line path attribution algorithms, GIG is uniquely robust since it will still yield Shapley values for atomic games modeled by decision trees.
[9]：Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads
标题：Auto-MAP：一个用于研究DNN工作负载的分布式执行计划的DQN框架
作者：Siyu Wang, Yi Rong, Shiqing Fan, Zhen Zheng, LanSong Diao, Guoping Long, Jun Yang, Xiaoyong Liu, Wei Lin
链接：https://arxiv.org/abs/2007.04069
摘要：The last decade has witnessed growth in the computational requirements for training deep neural networks. Current approaches (e.g., data/model parallelism, pipeline parallelism) parallelize training tasks onto multiple devices. However, these approaches always rely on specific deep learning frameworks and requires elaborate manual design, which make it difficult to maintain and share between different type of models. In this paper, we propose Auto-MAP, a framework for exploring distributed execution plans for DNN workloads, which can automatically discovering fast parallelization strategies through reinforcement learning on IR level of deep learning models. Efficient exploration remains a major challenge for reinforcement learning. We leverage DQN with task-specific pruning strategies to help efficiently explore the search space including optimized strategies. Our evaluation shows that Auto-MAP can find the optimal solution in two hours, while achieving better throughput on several NLP and convolution models.
[10]：Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence
标题：非殖民化人工智能：作为人工智能社会技术远见的非殖民化理论
作者：Shakir Mohamed, Marie-Therese Png, William Isaac
备注：28 Pages. Accepted, to appear in: Philosophy and Technology (405), Springer. Submitted 16 January, Accepted 26 May 2020
链接：https://arxiv.org/abs/2007.04068
摘要：This paper explores the important role of critical science, and in particular of post-colonial and decolonial theories, in understanding and shaping the ongoing advances in artificial intelligence. Artificial Intelligence (AI) is viewed as amongst the technological advances that will reshape modern societies and their relations. Whilst the design and deployment of systems that continually adapt holds the promise of far-reaching positive change, they simultaneously pose significant risks, especially to already vulnerable peoples. Values and power are central to this discussion. Decolonial theories use historical hindsight to explain patterns of power that shape our intellectual, political, economic, and social world. By embedding a decolonial critical approach within its technical practice, AI communities can develop foresight and tactics that can better align research and technology development with established ethical principles, centring vulnerable peoples who continue to bear the brunt of negative impacts of innovation and scientific progress. We highlight problematic applications that are instances of coloniality, and using a decolonial lens, submit three tactics that can form a decolonial field of artificial intelligence: creating a critical technical practice of AI, seeking reverse tutelage and reverse pedagogies, and the renewal of affective and political communities. The years ahead will usher in a wave of new scientific breakthroughs and technologies driven by AI research, making it incumbent upon AI communities to strengthen the social contract through ethical foresight and the multiplicity of intellectual perspectives available to us; ultimately supporting future technologies that enable greater well-being, with the goal of beneficence and justice for all.
[11]：Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
标题：PID-Lagrangian方法在强化学习中的响应安全性
作者：Adam Stooke, Joshua Achiam, Pieter Abbeel
备注：ICML 2020
链接：https://arxiv.org/abs/2007.03964
摘要：Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-violating behavior during agent training. We address this shortcoming by proposing a novel Lagrange multiplier update method that utilizes derivatives of the constraint function. We take a controls perspective, wherein the traditional Lagrange multiplier update behaves as \emph{integral} control; our terms introduce \emph{proportional} and \emph{derivative} control, achieving favorable learning dynamics through damping and predictive measures. We apply our PID Lagrangian methods in deep RL, setting a new state of the art in Safety Gym, a safe RL benchmark. Lastly, we introduce a new method to ease controller tuning by providing invariance to the relative numerical scales of reward and cost. Our extensive experiments demonstrate improved performance and hyperparameter robustness, while our algorithms remain nearly as simple to derive and implement as the traditional Lagrangian approach.
[12]：Non-parametric Models for Non-negative Functions
标题：非负函数的非参数模型
作者：Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi
链接：https://arxiv.org/abs/2007.03926
摘要：Linear models have shown great effectiveness and flexibility in many fields such as machine learning, signal processing and statistics. They can represent rich spaces of functions while preserving the convexity of the optimization problems where they are used, and are simple to evaluate, differentiate and integrate. However, for modeling non-negative functions, which are crucial for unsupervised learning, density estimation, or non-parametric Bayesian methods, linear models are not applicable directly. Moreover, current state-of-the-art models like generalized linear models either lead to non-convex optimization problems, or cannot be easily integrated. In this paper we provide the first model for non-negative functions which benefits from the same good properties of linear models. In particular, we prove that it admits a representer theorem and provide an efficient dual formulation for convex problems. We study its representation power, showing that the resulting space of functions is strictly richer than that of generalized linear models. Finally we extend the model and the theoretical results to functions with outputs in convex cones. The paper is complemented by an experimental evaluation of the model showing its effectiveness in terms of formulation, algorithmic derivation and practical results on the problems of density estimation, regression with heteroscedastic errors, and multiple quantile regression.
[13]：Towards a practical measure of interference for reinforcement learning
标题：强化学习中干扰的一种实用措施
作者：Vincent Liu, Adam White, Hengshuai Yao, Martha White
备注：18 pages
链接：https://arxiv.org/abs/2007.03807
摘要：Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. But, before we overcome interference we must understand it better. In this work, we provide a definition of interference for control in reinforcement learning. We systematically evaluate our new measures, by assessing correlation with several measures of learning performance, including stability, sample efficiency, and online and offline control performance across a variety of learning architectures. Our new interference measure allows us to ask novel scientific questions about commonly used deep learning architectures. In particular we show that target network frequency is a dominating factor for interference, and that updates on the last layer result in significantly higher interference than updates internal to the network. This new measure can be expensive to compute; we conclude with motivation for an efficient proxy measure and empirically demonstrate it is correlated with our definition of interference.
[14]：Near Optimal Provable Uniform Convergence in Off-Policy Evaluation for Reinforcement Learning
标题：强化学习非策略评价中的近最优可证明一致收敛性
作者：Ming Yin, Yu Bai, Yu-Xiang Wang
备注：Appendix included
链接：https://arxiv.org/abs/2007.03760
摘要：The Off-Policy Evaluation aims at estimating the performance of target policy $\pi$ using offline data rolled in by a logging policy $\mu$. Intensive studies have been conducted and the recent marginalized importance sampling (MIS) achieves the sample efficiency for OPE. However, it is rarely known if uniform convergence guarantees in OPE can be obtained efficiently. In this paper, we consider this new question and reveal the comprehensive relationship between OPE and offline learning for the first time. For the global policy class, by using the fully model-based OPE estimator, our best result is able to achieve $\epsilon$-uniform convergence with complexity $\widetilde{O}(H^3\cdot\min(S,H)/d_m\epsilon^2)$, where $d_m$ is an instance-dependent quantity decided by $\mu$. This result is only one factor away from our uniform convergence lower bound up to a logarithmic factor. For the local policy class, $\epsilon$-uniform convergence is achieved with the optimal complexity $\widetilde{O}(H^3/d_m\epsilon^2)$ in the off-policy setting. This result complements the work of sparse model-based planning (Agarwal et al. 2019) with generative model. Lastly, one interesting corollary of our intermediate result implies a refined analysis over simulation lemma.CV方向重复(1篇)
[1]：On the Generalization Effects of Linear Transformations in Data Augmentation
标题：数据扩充中线性变换的泛化效应
作者：Sen Wu, Hongyang R. Zhang, Gregory Valiant, Christopher Ré
备注：International Conference on Machine learning (ICML) 2020. Added experimental results on ImageNet
链接：https://arxiv.org/abs/2005.00695
摘要：Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. Yet, there is little rigorous understanding of why and how various augmentations work. In this work, we consider a family of linear transformations and study their effects on the ridge estimator in an over-parametrized linear regression setting. First, we show that transformations which preserve the labels of the data can improve estimation by enlarging the span of the training data. Second, we show that transformations which mix data can improve estimation by playing a regularization effect. Finally, we validate our theoretical insights on MNIST. Based on the insights, we propose an augmentation scheme that searches over the space of transformations by how uncertain the model is about the transformed data. We validate our proposed scheme on image and text datasets. For example, our method outperforms RandAugment by 1.24% on CIFAR-100 using Wide-ResNet-28-10. Furthermore, we achieve comparable accuracy to the SoTA Adversarial AutoAugment on CIFAR datasets.NLP方向重复(4篇)
[1]：Unsupervised Online Grounding of Natural Language during Human-Robot Interactions
标题：人机交互过程中自然语言的无监督在线接地
作者：Oliver Roesler
备注：11 pages, 6 figures, 3 tables; Published in Proceedings of the Second Grand Challenge and Workshop on Multimodal Language (Challenge-HML) in the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020)
链接：https://arxiv.org/abs/2007.04304
摘要：Allowing humans to communicate through natural language with robots requires connections between words and percepts. The process of creating these connections is called symbol grounding and has been studied for nearly three decades. Although many studies have been conducted, not many considered grounding of synonyms and the employed algorithms either work only offline or in a supervised manner. In this paper, a cross-situational learning based grounding framework is proposed that allows grounding of words and phrases through corresponding percepts without human supervision and online, i.e. it does not require any explicit training phase, but instead updates the obtained mappings for every new encountered situation. The proposed framework is evaluated through an interaction experiment between a human tutor and a robot, and compared to an existing unsupervised grounding framework. The results show that the proposed framework is able to ground words through their corresponding percepts online and in an unsupervised manner, while outperforming the baseline framework.
[2]：Chatbot: A Conversational Agent employed with Named Entity Recognition Model using Artificial Neural Network
标题：Chatbot：一种基于人工神经网络的命名实体识别模型的会话Agent
作者：Nazakat Ali
备注：10 pages
链接：https://arxiv.org/abs/2007.04248
摘要：Chatbot is a technology that is used to mimic human behavior using natural language. There are different types of Chatbot that can be used as conversational agent in various business domains in order to increase the customer service and satisfaction. For any business domain, it requires a knowledge base to be built for that domain and design an information retrieval based system that can respond the user with a piece of documentation or generated sentences. The core component of a Chatbot is Natural Language Understanding (NLU) which has been impressively improved by deep learning methods. But we often lack such properly built NLU modules and requires more time to build it from scratch for high quality conversations. This may encourage fresh learners to build a Chatbot from scratch with simple architecture and using small dataset, although it may have reduced functionality, rather than building high quality data driven methods. This research focuses on Named Entity Recognition (NER) and Intent Classification models which can be integrated into NLU service of a Chatbot. Named entities will be inserted manually in the knowledge base and automatically detected in a given sentence. The NER model in the proposed architecture is based on artificial neural network which is trained on manually created entities and evaluated using CoNLL-2003 dataset.
[3]：Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
标题：基于知识图的语义融合改进会话推荐系统
作者：Kun Zhou, Wayne Xin Zhao, Shuqing Bian, Yuanhang Zhou, Ji-Rong Wen, Jingsong Yu
链接：https://arxiv.org/abs/2007.04032
摘要：Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. Although several efforts have been made for CRS, two major issues still remain to be solved. First, the conversation data itself lacks of sufficient contextual information for accurately understanding users' preference. Second, there is a semantic gap between natural language expression and item-level user preference. To address these issues, we incorporate both word-oriented and entity-oriented knowledge graphs (KG) to enhance the data representations in CRSs, and adopt Mutual Information Maximization to align the word-level and entity-level semantic spaces. Based on the aligned semantic representations, we further develop a KG-enhanced recommender component for making accurate recommendations, and a KG-enhanced dialog component that can generate informative keywords or entities in the response text. Extensive experiments have demonstrated the effectiveness of our approach in yielding better performance on both recommendation and conversation tasks.
[4]：ISA: An Intelligent Shopping Assistant
标题：伊萨：一个聪明的购物助手
作者：Tuan Manh Lai, Trung Bui, Nedim Lipka
备注：6 pages, 5 figures
链接：https://arxiv.org/abs/2007.03805
摘要：Despite the growth of e-commerce, brick-and-mortar stores are still the preferred destinations for many people. In this paper, we present ISA, a mobile-based intelligent shopping assistant that is designed to improve shopping experience in physical stores. ISA assists users by leveraging advanced techniques in computer vision, speech processing, and natural language processing. An in-store user only needs to take a picture or scan the barcode of the product of interest, and then the user can talk to the assistant about the product. The assistant can also guide the user through the purchase process or recommend other similar products to the user. We take a data-driven approach in building the engines of ISA's natural language processing component, and the engines achieve good performance.
