April 2, 2020

3192 words 15 mins read

Paper Group ANR 98

Weight Priors for Learning Identity Relations. Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription. Reinforcement Learning for Mitigating Intermittent Interference in Terahertz Communication Networks. Modeling and solving a vehicle-sharing problem. Leveraging Frequency Analysis for Deep Fake Image Recognition. Quer …

Weight Priors for Learning Identity Relations


Title	Weight Priors for Learning Identity Relations
Authors	Kopparti Radha, Weyde Tillman
Abstract	Learning abstract and systematic relations has been an open issue in neural network learning for over 30 years. It has been shown recently that neural networks do not learn relations based on identity and are unable to generalize well to unseen data. The Relation Based Pattern (RBP) approach has been proposed as a solution for this problem. In this work, we extend RBP by realizing it as a Bayesian prior on network weights to model the identity relations. This weight prior leads to a modified regularization term in otherwise standard network learning. In our experiments, we show that the Bayesian weight priors lead to perfect generalization when learning identity based relations and do not impede general neural network learning. We believe that the approach of creating an inductive bias with weight priors can be extended easily to other forms of relations and will be beneficial for many other learning tasks.
Tasks
Published	2020-03-06
URL	https://arxiv.org/abs/2003.03125v1
PDF	https://arxiv.org/pdf/2003.03125v1.pdf
PWC	https://paperswithcode.com/paper/weight-priors-for-learning-identity-relations
Repo
Framework

Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription


Title	Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
Authors	Olivier Francon, Santiago Gonzalez, Babak Hodjat, Elliot Meyerson, Risto Miikkulainen, Xin Qiu, Hormoz Shahrzad
Abstract	There is now significant historical data available on decision making in organizations, consisting of the decision problem, what decisions were made, and how desirable the outcomes were. Using this data, it is possible to learn a surrogate model, and with that model, evolve a decision strategy that optimizes the outcomes. This paper introduces a general such approach, called Evolutionary Surrogate-Assisted Prescription, or ESP. The surrogate is, for example, a random forest or a neural network trained with gradient descent, and the strategy is a neural network that is evolved to maximize the predictions of the surrogate model. ESP is further extended in this paper to sequential decision-making tasks, which makes it possible to evaluate the framework in reinforcement learning (RL) benchmarks. Because the majority of evaluations are done on the surrogate, ESP is more sample efficient, has lower variance, and lower regret than standard RL approaches. Surprisingly, its solutions are also better because both the surrogate and the strategy network regularize the decision-making behavior. ESP thus forms a promising foundation to decision optimization in real-world problems.
Tasks	Decision Making
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05368v1
PDF	https://arxiv.org/pdf/2002.05368v1.pdf
PWC	https://paperswithcode.com/paper/effective-reinforcement-learning-through
Repo
Framework

Reinforcement Learning for Mitigating Intermittent Interference in Terahertz Communication Networks


Title	Reinforcement Learning for Mitigating Intermittent Interference in Terahertz Communication Networks
Authors	Reza Barazideh, Omid Semiari, Solmaz Niknam, Balasubramaniam Natarajan
Abstract	Emerging wireless services with extremely high data rate requirements, such as real-time extended reality applications, mandate novel solutions to further increase the capacity of future wireless networks. In this regard, leveraging large available bandwidth at terahertz frequency bands is seen as a key enabler. To overcome the large propagation loss at these very high frequencies, it is inevitable to manage transmissions over highly directional links. However, uncoordinated directional transmissions by a large number of users can cause substantial interference in terahertz networks. While such interference will be received over short random time intervals, the received power can be large. In this work, a new framework based on reinforcement learning is proposed that uses an adaptive multi-thresholding strategy to efficiently detect and mitigate the intermittent interference from directional links in the time domain. To find the optimal thresholds, the problem is formulated as a multidimensional multi-armed bandit system. Then, an algorithm is proposed that allows the receiver to learn the optimal thresholds with very low complexity. Another key advantage of the proposed approach is that it does not rely on any prior knowledge about the interference statistics, and hence, it is suitable for interference mitigation in dynamic scenarios. Simulation results confirm the superior bit-error-rate performance of the proposed method compared with two traditional time-domain interference mitigation approaches.
Tasks
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04832v1
PDF	https://arxiv.org/pdf/2003.04832v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-for-mitigating
Repo
Framework


Title	Modeling and solving a vehicle-sharing problem
Authors	Miriam Enzi, Sophie N. Parragh, David Pisinger
Abstract	Motivated by the change in mobility patterns, we present a new modeling approach for the vehicle-sharing problem. We aim at assigning vehicles to user-trips so as to maximize savings compared to other modes of transport. We base our formulations on the minimum-cost and the multi-commodity flow problem. These formulations make the problem applicable in daily operations. In the analysis we discuss an optimal composition of a shared fleet, restricted sets of modes of transport, and variations of the objective function.
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.08207v1
PDF	https://arxiv.org/pdf/2003.08207v1.pdf
PWC	https://paperswithcode.com/paper/modeling-and-solving-a-vehicle-sharing
Repo
Framework

Leveraging Frequency Analysis for Deep Fake Image Recognition


Title	Leveraging Frequency Analysis for Deep Fake Image Recognition
Authors	Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz
Abstract	Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While these deep fake images have been thoroughly investigated in the image domain-a classical approach from the area of image forensics-an analysis in the frequency domain has been missing so far. In this paper, we address this shortcoming and our results reveal that in frequency space, GAN-generated images exhibit severe artifacts that can be easily identified. We perform a comprehensive analysis, showing that these artifacts are consistent across different neural network architectures, data sets, and resolutions. In a further investigation, we demonstrate that these artifacts are caused by upsampling operations found in all current GAN architectures, indicating a structural and fundamental problem in the way images are generated via GANs. Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.
Tasks
Published	2020-03-19
URL	https://arxiv.org/abs/2003.08685v2
PDF	https://arxiv.org/pdf/2003.08685v2.pdf
PWC	https://paperswithcode.com/paper/leveraging-frequency-analysis-for-deep-fake
Repo
Framework

Query-Efficient Correlation Clustering


Title	Query-Efficient Correlation Clustering
Authors	David García-Soriano, Konstantin Kutzkov, Francesco Bonchi, Charalampos Tsourakakis
Abstract	Correlation clustering is arguably the most natural formulation of clustering. Given n objects and a pairwise similarity measure, the goal is to cluster the objects so that, to the best possible extent, similar objects are put in the same cluster and dissimilar objects are put in different clusters. A main drawback of correlation clustering is that it requires as input the $\Theta(n^2)$ pairwise similarities. This is often infeasible to compute or even just to store. In this paper we study \emph{query-efficient} algorithms for correlation clustering. Specifically, we devise a correlation clustering algorithm that, given a budget of $Q$ queries, attains a solution whose expected number of disagreements is at most $3\cdot OPT + O(\frac{n^3}{Q})$, where $OPT$ is the optimal cost for the instance. Its running time is $O(Q)$, and can be easily made non-adaptive (meaning it can specify all its queries at the outset and make them in parallel) with the same guarantees. Up to constant factors, our algorithm yields a provably optimal trade-off between the number of queries $Q$ and the worst-case error attained, even for adaptive algorithms. Finally, we perform an experimental study of our proposed method on both synthetic and real data, showing the scalability and the accuracy of our algorithm.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11557v1
PDF	https://arxiv.org/pdf/2002.11557v1.pdf
PWC	https://paperswithcode.com/paper/query-efficient-correlation-clustering
Repo
Framework

A latent variable approach to heat load prediction in thermal grids


Title	A latent variable approach to heat load prediction in thermal grids
Authors	Johan Simonsson, Khalid Tourkey Atta, Dave Zachariah, Wolfgang Birk
Abstract	In this paper a new method for heat load prediction in district energy systems is proposed. The method uses a nominal model for the prediction of the outdoor temperature dependent space heating load, and a data driven latent variable model to predict the time dependent residual heat load. The residual heat load arises mainly from time dependent operation of space heating and ventilation, and domestic hot water production. The resulting model is recursively updated on the basis of a hyper-parameter free implementation that results in a parsimonious model allowing for high computational performance. The approach is applied to a single multi-dwelling building in Lulea, Sweden, predicting the heat load using a relatively small number of model parameters and easily obtained measurements. The results are compared with predictions using an artificial neural network, showing that the proposed method achieves better prediction accuracy for the validation case. Additionally, the proposed methods exhibits explainable behavior through the use of an interpretable physical model.
Tasks
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05397v1
PDF	https://arxiv.org/pdf/2002.05397v1.pdf
PWC	https://paperswithcode.com/paper/a-latent-variable-approach-to-heat-load
Repo
Framework

Contextual Search for General Hypothesis Classes


Title	Contextual Search for General Hypothesis Classes
Authors	Allen Liu, Renato Paes Leme, Jon Schneider
Abstract	We study a general version of the problem of online learning under binary feedback: there is a hidden function $f : \mathcal{X} \rightarrow \mathcal{Y}$ in a certain hypothesis class $\mathcal{H}$. A learner is given adversarially chosen inputs (contexts) $x_t \in \mathcal{X}$ and is asked to submit a guess $y_t \in \mathcal{Y}$ for the value $f(x_t)$. Upon guessing the learner incurs a certain loss $L(y_t, f(x_t))$ and learns whether $y_t \leq f(x_t)$ or $y_t > f(x_t)$. The special case where $\mathcal{H}$ is the class of linear functions over the unit ball has been studied in a series of papers. We both generalize and improve these results. We provide a $O(d^2)$ regret bound where $d$ is the covering dimension of the hypothesis class. The algorithms are based on a novel technique which we call Steiner potential since in the linear case it reduces to controlling the value of the Steiner polynomial of a convex region at various scales. We also show that this new technique provides optimal regret (up to log factors) in the linear case (i.e. the original contextual search problem), improving the previously known bound of $O(d^4)$ to $O(d \log d)$. Finally, we extend these results to a noisy feedback model, where each round our feedback is flipped with fixed probability $p < 1/2$.
Tasks
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01703v1
PDF	https://arxiv.org/pdf/2003.01703v1.pdf
PWC	https://paperswithcode.com/paper/contextual-search-for-general-hypothesis
Repo
Framework

KBSET – Knowledge-Based Support for Scholarly Editing and Text Processing with Declarative LaTeX Markup and a Core Written in SWI-Prolog


Title	KBSET – Knowledge-Based Support for Scholarly Editing and Text Processing with Declarative LaTeX Markup and a Core Written in SWI-Prolog
Authors	Jana Kittelmann, Christoph Wernhard
Abstract	KBSET is an environment that provides support for scholarly editing in two flavors: First, as a practical tool KBSET/Letters that accompanies the development of editions of correspondences (in particular from the 18th and 19th century), completely from source documents to PDF and HTML presentations. Second, as a prototypical tool KBSET/NER for experimentally investigating novel forms of working on editions that are centered around automated named entity recognition. KBSET can process declarative application-specific markup that is expressed in LaTeX notation and incorporate large external fact bases that are typically provided in RDF. KBSET includes specially developed LaTeX styles and a core system that is written in SWI-Prolog, which is used there in many roles, utilizing that it realizes the potential of Prolog as a unifying language.
Tasks	Named Entity Recognition
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10329v1
PDF	https://arxiv.org/pdf/2002.10329v1.pdf
PWC	https://paperswithcode.com/paper/kbset-knowledge-based-support-for-scholarly-1
Repo
Framework

Applying Rule-Based Context Knowledge to Build Abstract Semantic Maps of Indoor Environments


Title	Applying Rule-Based Context Knowledge to Build Abstract Semantic Maps of Indoor Environments
Authors	Ziyuan Liu, Georg von Wichert
Abstract	In this paper, we propose a generalizable method that systematically combines data driven MCMC samplingand inference using rule-based context knowledge for data abstraction. In particular, we demonstrate the usefulness of our method in the scenario of building abstract semantic maps for indoor environments. The product of our system is a parametric abstract model of the perceived environment that not only accurately represents the geometry of the environment but also provides valuable abstract information which benefits high-level robotic applications. Based on predefined abstract terms,such as type and relation, we define task-specific context knowledge as descriptive rules in Markov Logic Networks. The corresponding inference results are used to construct a priordistribution that aims to add reasonable constraints to the solution space of semantic maps. In addition, by applying a semantically annotated sensor model, we explicitly use context information to interpret the sensor data. Experiments on real world data show promising results and thus confirm the usefulness of our system.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.10938v1
PDF	https://arxiv.org/pdf/2002.10938v1.pdf
PWC	https://paperswithcode.com/paper/applying-rule-based-context-knowledge-to
Repo
Framework

Blocked Clusterwise Regression


Title	Blocked Clusterwise Regression
Authors	Max Cytrynbaum
Abstract	A recent literature in econometrics models unobserved cross-sectional heterogeneity in panel data by assigning each cross-sectional unit a one-dimensional, discrete latent type. Such models have been shown to allow estimation and inference by regression clustering methods. This paper is motivated by the finding that the clustered heterogeneity models studied in this literature can be badly misspecified, even when the panel has significant discrete cross-sectional structure. To address this issue, we generalize previous approaches to discrete unobserved heterogeneity by allowing each unit to have multiple, imperfectly-correlated latent variables that describe its response-type to different covariates. We give inference results for a k-means style estimator of our model and develop information criteria to jointly select the number clusters for each latent variable. Monte Carlo simulations confirm our theoretical results and give intuition about the finite-sample performance of estimation and model selection. We also contribute to the theory of clustering with an over-specified number of clusters and derive new convergence rates for this setting. Our results suggest that over-fitting can be severe in k-means style estimators when the number of clusters is over-specified.
Tasks	Model Selection
Published	2020-01-29
URL	https://arxiv.org/abs/2001.11130v1
PDF	https://arxiv.org/pdf/2001.11130v1.pdf
PWC	https://paperswithcode.com/paper/blocked-clusterwise-regression
Repo
Framework

Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory


Title	Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
Authors	Nabiha Asghar, Ivan Kobyzev, Jesse Hoey, Pascal Poupart, Muhammad Bilal Sheikh
Abstract	State-of-the-art neural dialogue systems excel at syntactic and semantic modelling of language, but often have a hard time establishing emotional alignment with the human interactant during a conversation. In this work, we bring Affect Control Theory (ACT), a socio-mathematical model of emotions for human-human interactions, to the neural dialogue generation setting. ACT makes predictions about how humans respond to emotional stimuli in social situations. Due to this property, ACT and its derivative probabilistic models have been successfully deployed in several applications of Human-Computer Interaction, including empathetic tutoring systems, assistive healthcare devices and two-person social dilemma games. We investigate how ACT can be used to develop affect-aware conversational agents, which produce emotionally aligned responses to prompts and take into consideration the affective identities of the interactants.
Tasks	Dialogue Generation
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03645v1
PDF	https://arxiv.org/pdf/2003.03645v1.pdf
PWC	https://paperswithcode.com/paper/generating-emotionally-aligned-responses-in
Repo
Framework

Low-Resource Knowledge-Grounded Dialogue Generation


Title	Low-Resource Knowledge-Grounded Dialogue Generation
Authors	Xueliang Zhao, Wei Wu, Chongyang Tao, Can Xu, Dongyan Zhao, Rui Yan
Abstract	Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain. Motivated by the challenge in practice, we consider knowledge-grounded dialogue generation under a natural assumption that only limited training examples are available. In such a low-resource setting, we devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model. By this means, the major part of the model can be learned from a large number of ungrounded dialogues and unstructured documents, while the remaining small parameters can be well fitted using the limited training examples. Evaluation results on two benchmarks indicate that with only 1/8 training data, our model can achieve the state-of-the-art performance and generalize well on out-of-domain knowledge.
Tasks	Dialogue Generation
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10348v1
PDF	https://arxiv.org/pdf/2002.10348v1.pdf
PWC	https://paperswithcode.com/paper/low-resource-knowledge-grounded-dialogue-1
Repo
Framework

Non-Autoregressive Neural Dialogue Generation


Title	Non-Autoregressive Neural Dialogue Generation
Authors	Qinghong Han, Yuxian Meng, Fei Wu, Jiwei Li
Abstract	Maximum Mutual information (MMI), which models the bidirectional dependency between responses ($y$) and contexts ($x$), i.e., the forward probability $\log p(yx)$ and the backward probability $\log p(xy)$, has been widely used as the objective in the \sts model to address the dull-response issue in open-domain dialog generation. Unfortunately, under the framework of the \sts model, direct decoding from $\log p(yx) + \log p(xy)$ is infeasible since the second part (i.e., $p(xy)$) requires the completion of target generation before it can be computed, and the search space for $y$ is enormous. Empirically, an N-best list is first generated given $p(yx)$, and $p(xy)$ is then used to rerank the N-best list, which inevitably results in non-globally-optimal solutions. In this paper, we propose to use non-autoregressive (non-AR) generation model to address this non-global optimality issue. Since target tokens are generated independently in non-AR generation, $p(xy)$ for each target word can be computed as soon as it’s generated, and does not have to wait for the completion of the whole sequence. This naturally resolves the non-global optimal issue in decoding. Experimental results demonstrate that the proposed non-AR strategy produces more diverse, coherent, and appropriate responses, yielding substantive gains in BLEU scores and in human evaluations.
Tasks	Dialogue Generation
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04250v2
PDF	https://arxiv.org/pdf/2002.04250v2.pdf
PWC	https://paperswithcode.com/paper/non-autoregressive-neural-dialogue-generation
Repo
Framework

Teaching Machines to Converse


Title	Teaching Machines to Converse
Authors	Jiwei Li
Abstract	The ability of a machine to communicate with humans has long been associated with the general success of AI. This dates back to Alan Turing’s epoch-making work in the early 1950s, which proposes that a machine’s intelligence can be tested by how well it, the machine, can fool a human into believing that the machine is a human through dialogue conversations. Many systems learn generation rules from a minimal set of authored rules or labels on top of hand-coded rules or templates, and thus are both expensive and difficult to extend to open-domain scenarios. Recently, the emergence of neural network models the potential to solve many of the problems in dialogue learning that earlier systems cannot tackle: the end-to-end neural frameworks offer the promise of scalability and language-independence, together with the ability to track the dialogue state and then mapping between states and dialogue actions in a way not possible with conventional systems. On the other hand, neural systems bring about new challenges: they tend to output dull and generic responses; they lack a consistent or a coherent persona; they are usually optimized through single-turn conversations and are incapable of handling the long-term success of a conversation; and they are not able to take the advantage of the interactions with humans. This dissertation attempts to tackle these challenges: Contributions are two-fold: (1) we address new challenges presented by neural network models in open-domain dialogue generation systems; (2) we develop interactive question-answering dialogue systems by (a) giving the agent the ability to ask questions and (b) training a conversation agent through interactions with humans in an online fashion, where a bot improves through communicating with humans and learning from the mistakes that it makes.
Tasks	Dialogue Generation, Question Answering
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11701v1
PDF	https://arxiv.org/pdf/2001.11701v1.pdf
PWC	https://paperswithcode.com/paper/teaching-machines-to-converse
Repo
Framework