Latest in

total 17869took 0.12s
Goal-conditioned Imitation LearningJun 13 2019Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where detecting whether ... More
Deep Reinforcement Learning for Cyber SecurityJun 13 2019The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive, and large-scale. ... More
Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its RankingJun 13 2019This paper focuses on the end-to-end abstractive summarization of a single product review without supervision. We assume that a review can be described as a discourse tree, in which the summary is the root, and the child sentences explain their parent ... More
KCAT: A Knowledge-Constraint Typing Annotation ToolJun 13 2019Fine-grained Entity Typing is a tough task which suffers from noise samples extracted from distant supervision. Thousands of manually annotated samples can achieve greater performance than millions of samples generated by the previous distant supervision ... More
Meta-heuristic for non-homogeneous peak density spaces and implementation on 2 real-world parameter learning/tuning applicationsJun 13 2019Observer effect in physics (/psychology) regards bias in measurement (/perception) due to the interference of instrument (/knowledge). Based on these concepts, a new meta-heuristic algorithm is proposed for controlling memory usage per localities without ... More
Compositional generalization through meta sequence-to-sequence learningJun 12 2019People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket." In contrast, powerful sequence-to-sequence (seq2seq) neural networks fail such tests of compositionality, especially when ... More
E3: Entailment-driven Extracting and Editing for Conversational Machine ReadingJun 12 2019Conversational machine reading systems help users answer high-level questions (e.g. determine if they qualify for particular government benefits) when they do not know the exact rules by which the determination is made(e.g. whether they need certain income ... More
Sub-Goal Trees -- a Framework for Goal-Directed Trajectory Prediction and OptimizationJun 12 2019Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction and optimization. ... More
COMET: Commonsense Transformers for Automatic Knowledge Graph ConstructionJun 12 2019We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with ... More
Efficient Exploration via State Marginal MatchingJun 12 2019To solve tasks with sparse rewards, reinforcement learning algorithms must be equipped with suitable exploration techniques. However, it is unclear what underlying objective is being optimized by existing exploration algorithms, or how they can be altered ... More
Representation Learning for Words and EntitiesJun 12 2019This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning representations of words ... More
Search on the Replay Buffer: Bridging Planning and Reinforcement LearningJun 12 2019The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning. Planning algorithms effectively reason over long horizons, but assume access to a local policy and distance ... More
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading ComprehensionJun 12 2019Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble ... More
Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-ElitesJun 12 2019We propose the use of quality-diversity algorithms for mixed-initiative game content generation. This idea is implemented as a new feature of the Evolutionary Dungeon Designer, a system for mixed-initiative design of the type of levels you typically find ... More
General Video Game Rule GenerationJun 12 2019We introduce the General Video Game Rule Generation problem, and the eponymous software framework which will be used in a new track of the General Video Game AI (GVGAI) competition. The problem is, given a game level as input, to generate the rules of ... More
Evaluation of Dataflow through layers of Deep Neural Networks in Classification and Regression ProblemsJun 12 2019This paper introduces two straightforward, effective indices to evaluate the input data and the data flowing through layers of a feedforward deep neural network. For classification problems, the separation rate of target labels in the space of dataflow ... More
Polynomial-time Updates of Epistemic States in a Fragment of Probabilistic Epistemic Argumentation (Technical Report)Jun 12 2019Probabilistic epistemic argumentation allows for reasoning about argumentation problems in a way that is well founded by probability theory. Epistemic states are represented by probability functions over possible worlds and can be adjusted to new beliefs ... More
Fast Task Inference with Variational Intrinsic Successor FeaturesJun 12 2019It has been established that diverse behaviors spanning the controllable subspace of an Markov decision process can be trained by rewarding a policy for being distinguishable from other policies \citep{gregor2016variational, eysenbach2018diversity, warde2018unsupervised}. ... More
Deep Reinforcement Learning for Unmanned Aerial Vehicle-Assisted Vehicular NetworksJun 12 2019Unmanned aerial vehicles (UAVs) are envisioned to complement the 5G communication infrastructure in future smart cities. Hot spots easily appear in road intersections, where effective communication among vehicles is challenging. UAVs may serve as relays ... More
Neural Variational Inference For Estimating Uncertainty in Knowledge Graph EmbeddingsJun 12 2019Recent advances in Neural Variational Inference allowed for a renaissance in latent variable models in a variety of domains involving high-dimensional data. While traditional variational methods derive an analytical approximation for the intractable distribution ... More
Unsupervised Question Answering by Cloze TranslationJun 12 2019Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high quality training data is actually ... More
Joint Reasoning for Temporal and Causal RelationsJun 12 2019Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must be before its effect in time, temporal and causal relations are closely related and one relation even dictates the other ... More
Sionnx: Automatic Unit Test Generator for ONNX ConformanceJun 12 2019Open Neural Network Exchange (ONNX) is an open format to represent AI models and is supported by many machine learning frameworks. While ONNX defines unified and portable computation operators across various frameworks, the conformance tests for those ... More
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural NetworksJun 12 2019Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many applications ranging from robustness certification of classifiers to stability analysis of closed-loop systems with reinforcement learning controllers. Existing ... More
Understanding artificial intelligence ethics and safetyJun 11 2019A remarkable time of human promise has been ushered in by the convergence of the ever-expanding availability of big data, the soaring speed and stretch of cloud computing platforms, and the advancement of increasingly sophisticated machine learning algorithms. ... More
Toward Best Practices for Explainable B2B Machine LearningJun 11 2019To design tools and data pipelines for explainable B2B machine learning (ML) systems, we need to recognize not only the immediate audience of such tools and data, but also (1) their organizational context and (2) secondary audiences. Our learnings are ... More
Issues with post-hoc counterfactual explanations: a discussionJun 11 2019Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier. However, the assumptions they make about the data and the classifier make them unreliable ... More
Using Structured Representation and Data: A Hybrid Model for Negation and Sentiment in Customer Service ConversationsJun 11 2019Twitter customer service interactions have recently emerged as an effective platform to respond and engage with customers. In this work, we explore the role of negation in customer service interactions, particularly applied to sentiment analysis. We define ... More
Two-step Constructive Approaches for Dungeon GenerationJun 11 2019This paper presents a two-step generative approach for creating dungeons in the rogue-like puzzle game MiniDungeons 2. Generation is split into two steps, initially producing the architectural layout of the level as its walls and floor tiles, and then ... More
Trip Table Estimation and Prediction for Dynamic Traffic Assignment ApplicationsJun 11 2019The study focuses on estimating and predicting time-varying origin to destination (OD) trip tables for a dynamic traffic assignment (DTA) model. A bi-level optimisation problem is formulated and solved to estimate OD flows from pre-existent demand matrix ... More
WikiDataSets : Standardized sub-graphs from WikiDataJun 11 2019Developing new ideas and algorithms in the fields of graph processing and relational learning requires datasets to work with and WikiData is the largest open source knowledge graph involving more than fifty millions entities. It is larger than needed ... More
Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement LearningJun 11 2019Recent developments in deep reinforcement learning are concerned with creating decision-making agents which can perform well in various complex domains. A particular approach which has received increasing attention is multi-agent reinforcement learning, ... More
Reinforcement Learning of Minimalist Numeral GrammarsJun 11 2019Speech-controlled user interfaces facilitate the operation of devices and household functions to laymen. State-of-the-art language technology scans the acoustically analyzed speech signal for relevant keywords that are subsequently inserted into semantic ... More
Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game JassJun 11 2019In the last decades we have witnessed the success of applications of Artificial Intelligence to playing games. In this work we address the challenging field of games with hidden information and card games in particular. Jass is a very popular card game ... More
Online Learning and Planning in Partially Observable Domains without Prior KnowledgeJun 11 2019How an agent can act optimally in stochastic, partially observable domains is a challenge problem, the standard approach to address this issue is to learn the domain model firstly and then based on the learned model to find the (near) optimal policy. ... More
Learning Powerful Policies by Using Consistent Dynamics ModelJun 11 2019Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based approaches lead to `compounding ... More
Importance Resampling for Off-policy PredictionJun 11 2019Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the weights for the value function. In this work, we explore ... More
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution CorrectionsJun 10 2019In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate ... More
Self-Supervised Exploration via DisagreementJun 10 2019Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments ... More
Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic InteractionJun 10 2019We present a new research task and a dataset to understand human social interactions via computational methods, to ultimately endow machines with the ability to encode and decode a broad channel of social signals humans use. This research direction is ... More
Tackling Climate Change with Machine LearningJun 10 2019Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt ... More
Detecting Everyday Scenarios in Narrative TextsJun 10 2019Script knowledge consists of detailed information on everyday activities. Such information is often taken for granted in text and needs to be inferred by readers. Therefore, script knowledge is a central component to language comprehension. Previous work ... More
GLTR: Statistical Detection and Visualization of Generated TextJun 10 2019The rapid improvement of language models has raised the specter of abuse of text generation systems. This progress motivates the development of simple methods for detecting generated text that can be used by and explained to non-experts. We develop GLTR, ... More
"Did You Hear That?" Learning to Play Video Games from Audio CuesJun 10 2019Jun 11 2019Game-playing AI research has focused for a long time on learning to play video games from visual input or symbolic information. However, humans benefit from a wider array of sensors which we utilise in order to navigate the world around us. In particular, ... More
Project Thyia: A Forever GameplayerJun 10 2019The space of Artificial Intelligence entities is dominated by conversational bots. Some of them fit in our pockets and we take them everywhere we go, or allow them to be a part of human homes. Siri, Alexa, they are recognised as present in our world. ... More
Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the PastJun 10 2019Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates with an actor-critic formulation, SAC achieves state-of-the-art performance ... More
The Riddle of TogelbyJun 10 2019At the 2017 Artificial and Computational Intelligence in Games meeting at Dagstuhl, Julian Togelius asked how to make spaces where every way of filling in the details yielded a good game. This study examines the possibility of enriching search spaces ... More
Automatic Algorithm Selection In Multi-agent PathfindingJun 10 2019In a multi-agent pathfinding (MAPF) problem, agents need to navigate from their start to their goal locations without colliding into each other. There are various MAPF algorithms, including Windowed Hierarchical Cooperative A*, Flow Annotated Replanning, ... More
Autonomous Goal Exploration using Learned Goal Spaces for Visuomotor Skill Acquisition in RobotsJun 10 2019The automatic and efficient discovery of skills, without supervision, for long-living autonomous agents, remains a challenge of Artificial Intelligence. Intrinsically Motivated Goal Exploration Processes give learning agents a human-inspired mechanism ... More
FaRM: Fair Reward Mechanism for Information Aggregation in Spontaneous Localized Settings (Extended Version)Jun 10 2019Although peer prediction markets are widely used in crowdsourcing to aggregate information from agents, they often fail to reward the participating agents equitably. Honest agents can be wrongly penalized if randomly paired with dishonest ones. In this ... More
Best-First Width Search for Multi Agent Privacy-preserving PlanningJun 10 2019In multi-agent planning, preserving the agents' privacy has become an increasingly popular research topic. For preserving the agents' privacy, agents jointly compute a plan that achieves mutual goals by keeping certain information private to the individual ... More
A Survey of Reinforcement Learning Informed by Natural LanguageJun 10 2019To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language ... More
Learning to combine Grammatical Error CorrectionsJun 10 2019The field of Grammatical Error Correction (GEC) has produced various systems to deal with focused phenomena or general text editing. We propose an automatic way to combine black-box systems. Our method automatically detects the strength of a system or ... More
DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic InteractionsJun 10 2019We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be inferred from the ... More
DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic InteractionsJun 10 2019Jun 11 2019We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be inferred from the ... More
Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination PatternsJun 10 2019As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define individuals, but ... More
Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictionsJun 10 2019Soil moisture is an important variable that determines floods, vegetation health, agriculture productivity, and land surface feedbacks to the atmosphere, etc. Accurately modeling soil moisture has important implications in both weather and climate models. ... More
Generative Continual Concept LearningJun 10 2019After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently ... More
Write, Execute, Assess: Program Synthesis with a REPLJun 09 2019We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs. We equip the search process with an interpreter or a read-eval-print-loop (REPL), which immediately ... More
Curiosity-Driven Multi-Criteria Hindsight Experience ReplayJun 09 2019Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot ... More
Question Answering as Global Reasoning over Semantic AbstractionsJun 09 2019We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. ... More
Gossip-based Actor-Learner Architectures for Deep Reinforcement LearningJun 09 2019Multi-simulator training has contributed to the recent success of Deep Reinforcement Learning by stabilizing learning and allowing for higher training throughputs. We propose Gossip-based Actor-Learner Architectures (GALA) where several actor-learners ... More
There is no general AI: Why Turing machines cannot pass the Turing testJun 09 2019Since 1950, when Alan Turing proposed what has since come to be called the Turing test, the ability of a machine to pass this test has established itself as the primary hallmark of general AI. To pass the test, a machine would have to be able to engage ... More
Federated AI lets a team imagine together: Federated Learning of GANsJun 09 2019Envisioning a new imaginative idea together is a popular human need. Imagining together as a team can often lead to breakthrough ideas, but the collaboration effort can also be challenging, especially when the team members are separated by time and space. ... More
Transfer Learning by Modeling a Distribution over PoliciesJun 09 2019Exploration and adaptation to new tasks in a transfer learning setup is a central challenge in reinforcement learning. In this work, we build on the idea of modeling a distribution over policies in a Bayesian deep reinforcement learning setup to propose ... More
Guidelines for Responsible and Human-Centered Use of Explainable Machine LearningJun 08 2019Explainable machine learning (ML) has been implemented in numerous open source and proprietary software packages and explainable ML is an important aspect of commercial predictive modeling. However, explainable ML can be misused, particularly as a faulty ... More
Strategies to architect AI Safety: Defense to guard AI from AdversariesJun 08 2019The impact of designing for security of AI is critical for humanity in the AI era. With humans increasingly becoming dependent upon AI, there is a need for neural networks that work reliably, inspite of Adversarial attacks. The vision for Safe and secure ... More
A Ride-Matching Strategy For Large Scale Dynamic Ridesharing Services Based on Polar CoordinatesJun 08 2019In this paper, we study a challenging problem of how to pool multiple ride-share trip requests in real time under an uncertain environment. The goals are better performance metrics of efficiency and acceptable satisfaction of riders. To solve the problem ... More
Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance SamplingJun 08 2019Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) --- the problem of evaluating a new policy using the historical data obtained by different ... More
Global Semantic Description of Objects based on Prototype TheoryJun 08 2019In this paper, we introduce a novel semantic description approach inspired on Prototype Theory foundations. We propose a Computational Prototype Model (CPM) that encodes and stores the central semantic meaning of objects category: the semantic prototype. ... More
Watch, Try, Learn: Meta-Learning from Demonstrations and RewardJun 07 2019Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards enabling agents ... More
Classifying the reported ability in clinical mobility descriptionsJun 07 2019Assessing how individuals perform different activities is key information for modeling health states of individuals and populations. Descriptions of activity performance in clinical free text are complex, including syntactic negation and similarities ... More
Extension of Rough Set Based on Positive Transitive RelationJun 07 2019Jun 13 2019The application of rough set theory in incomplete information systems is a key problem in practice since missing values almost always occur in knowledge acquisition due to the error of data measuring, the limitation of data collection, or the limitation ... More
DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep NetworksJun 07 2019Deep neural networks (DNNs) have achieved state-of-the-art performances in many important domains, including medical diagnosis, security, and autonomous driving. In these domains where safety is highly critical, an erroneous decision can result in serious ... More
Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion GuaranteesJun 07 2019We introduce and analyze two parameter-free linear-memory tree search algorithms. Under mild assumptions we prove our algorithms are guaranteed to perform only a logarithmic factor more node expansions than A* when the search space is a tree. Previously, ... More
Matching the Blanks: Distributional Similarity for Relation LearningJun 07 2019General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed ... More
Shared-Private Bilingual Word Embeddings for Neural Machine TranslationJun 07 2019Word embedding is central to neural machine translation (NMT), which has attracted intensive research interest in recent years. In NMT, the source embedding plays the role of the entrance while the target embedding acts as the terminal. These layers occupy ... More
DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural NetworksJun 07 2019Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely on accurate registration between an atlas and the tractograms of an individual, ... More
Active inference body perception and action for humanoid robotsJun 07 2019One of the biggest challenges in robotics systems is interacting under uncertainty. Unlike robots, humans learn, adapt and perceive their body as a unity when interacting with the world. We hypothesize that the nervous system counteracts sensor and motor ... More
Multi-hop Reading Comprehension through Question Decomposition and RescoringJun 07 2019Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question into simpler sub-questions that can be answered by off-the-shelf single-hop ... More
Compositional Questions Do Not Necessitate Multi-hop ReasoningJun 07 2019Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct large multi-hop RC datasets. For example, even highly compositional questions ... More
Worst-Case Regret Bounds for Exploration via Randomized Value FunctionsJun 07 2019This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with ... More
Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask TransferJun 07 2019Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and robustness. ... More
Improving Exploration in Soft-Actor-Critic with Normalizing Flows PoliciesJun 06 2019Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \cut{being}sample inefficient. Soft Actor Critic (SAC) proposes an off-policy deep actor critic algorithm within the maximum ... More
Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLPJun 06 2019The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a "lucky" sub-network initialization being present rather than by helping the optimization process. This phenomenon ... More
Conversing by Reading: Contentful Neural Conversation with On-demand Machine ReadingJun 06 2019Jun 07 2019Although neural conversation models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to contentful ... More
Conversing by Reading: Contentful Neural Conversation with On-demand Machine ReadingJun 06 2019Although neural conversation models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to contentful ... More
Adaptive Gradient-Based Meta-Learning MethodsJun 06 2019We build a theoretical framework for understanding practical meta-learning methods that enables the integration of sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. ... More
Scaling Autoregressive Video ModelsJun 06 2019Due to the statistical complexity of video, the high degree of inherent stochasticity, and the sheer amount of data, generating natural video remains a challenging task. State-of-the-art video generation models attempt to address these issues by combining ... More
Flexibly Fair Representation Learning by DisentanglementJun 06 2019We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning ... More
Combining Reinforcement Learning and Configuration Checking for Maximum k-plex ProblemJun 06 2019The Maximum k-plex Problem is an important combinatorial optimization problem with increasingly wide applications. Due to its exponential time complexity, many heuristic methods have been proposed which can return a good-quality solution in a reasonable ... More
Localizing Catastrophic Forgetting in Neural NetworksJun 06 2019Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks. While this phenomenon was studied in the past, there is only very limited recent research on this phenomenon. We propose a method for determining ... More
Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert DomainsJun 06 2019Many complex discourse-level tasks can aid domain experts in their work but require costly expert annotations for data creation. To speed up and ease annotations, we investigate the viability of automatically generated annotation suggestions for such ... More
The Open Vault Challenge -- Learning how to build calibration-free interactive systems by cracking the code of a vaultJun 06 2019This demo takes the form of a challenge to the IJCAI community. A physical vault, secured by a 4-digit code, will be placed in the demo area. The author will publicly open the vault by entering the code on a touch-based interface, and as many times as ... More
Unsupervised Pivot Translation for Distant LanguagesJun 06 2019Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German translation), they perform poorly ... More
Clustered Reinforcement LearningJun 06 2019Exploration strategy design is one of the challenging problems in reinforcement learning~(RL), especially when the environment contains a large state space or sparse rewards. During exploration, the agent tries to discover novel areas or high reward~(quality) ... More
One-shot Information Extraction from Document Images using Neuro-Deductive Program SynthesisJun 06 2019Our interest in this paper is in meeting a rapidly growing industrial demand for information extraction from images of documents such as invoices, bills, receipts etc. In practice users are able to provide a very small number of example images labeled ... More
Uncertainty-guided Continual Learning with Bayesian Neural NetworksJun 06 2019Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning ... More
Ease-of-Teaching and Language Structure from Emergent CommunicationJun 06 2019Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure is often the ... More
Multi-view Knowledge Graph Embedding for Entity AlignmentJun 06 2019We study the problem of embedding-based entity alignment between knowledge graphs (KGs). Previous works mainly focus on the relational structure of entities. Some further incorporate another type of features, such as attributes, for refinement. However, ... More