In this paper, we propose a contrastive learning model for supervised abstractive text summarization, where we view a document, its gold summary and its model generated summaries as different views of the same mean representation and maximize the similarities between them during training.
In this task, the robot needs to first design a feasible bridge architecture for arbitrarily wide cliffs and then manipulate the blocks reliably to construct a stable bridge according to the proposed design.
Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase.
To tackle these two issues, we propose a novel technique called disentangled attention, which provides an intrinsic regularization for two robots to focus on separate sub-tasks and objects.
Under the FL framework and Differentially Private thinking, we propose a FederatedDifferentially Private Generative Adversarial Network (FedDPGAN) to detectCOVID-19 pneumonia for sustainable smart cities.
In this study, we classified different origins of three categories of herbal medicines with different feature extraction methods: manual feature extraction, mathematical transformation, deep learning algorithms.
Due to the inaccurate person detections and pose changes, pedestrian misalignment significantly increases the difficulty of feature extraction and matching.
We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems.
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games.
Proximal Policy Optimization (PPO) is a popular on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings.
no code implementations • 21 Jan 2021 • Yuan Fang, Ding Wang, Peng Li, Hang Su, Tian Le, Yi Wu, Guo-Wei Yang, Hua-Li Zhang, Zhi-Guang Xiao, Yan-Qiu Sun, Si-Yuan Hong, Yan-Wu Xie, Huan-Hua Wang, Chao Cao, Xin Lu, Hui-Qiu Yuan, Yang Liu
We report growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films on Si(111).
Mesoscale and Nanoscale Physics
We initiate the study on deep reinforcement learning problems that require low switching cost, i. e., small number of policy switches during training.
We benchmark commonly used multi-agent deep reinforcement learning (MARL) algorithms on a variety of cooperative multi-agent games.
In this paper, we analyze the pros and cons of each method and propose the regulated difference of inverse visitation counts as a simple but effective criterion for IR.
Using angle-resolved photoemission spectroscopy (ARPES) and low-energy electron diffraction (LEED), together with density-functional theory (DFT) calculation, we report the formation of charge density wave (CDW) and its interplay with the Kondo effect and topological states in CeSbTe.
Strongly Correlated Electrons Materials Science
In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.
We also find in experiments that our model is less dependent on sentence positions.
In this paper, we propose a streaming GNN model based on continual learning so that the model is trained incrementally and up-to-date node representations can be obtained at each time step.
Finally, we reconstruct the feature extractor to ensure that our model can obtain more richer and robust features.
In fact, due to the limitation of the receptive field, the 3 x 3 kernel has difficulty in covering the corresponding features at high/original resolution.
While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across tasks, and how the gradients from different tasks may interfere with each other.
Ranked #1 on Meta-Learning on MT50
Object detection is an essential step towards holistic scene understanding.
Ranked #157 on Object Detection on COCO test-dev
In multi-agent games, the complexity of the environment can grow exponentially as the number of agents increases, so it is particularly challenging to learn good policies when the agent population is large.
Previous database systems extended their SQL dialect to support ML.
We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents.
To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure.
Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent strategy, many of which require sophisticated tool use and coordination.
We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards.
Recommender systems are one of the most pervasive applications of machine learning in industry, with many services using them to match users to products or information.
Green Security Games (GSGs) have been proposed and applied to optimize patrols conducted by law enforcement agencies in green security domains such as combating poaching, illegal logging and overfishing.
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI.
This allows the system to achieve a smoother and more robust performance by optimizing in an alternate space.
Despite the recent successes of probabilistic programming languages (PPLs) in AI applications, PPLs offer only limited support for random variables whose distributions combine discrete and continuous elements.
Local polynomial regression (Fan and Gijbels 1996) is an important class of methods for nonparametric density estimation and regression problems.
To generalize to unseen environments, an agent needs to be robust to low-level variations (e. g. color, texture, object changes), and also high-level variations (e. g. layout changes of the environment).
Gesture is a natural interface in interacting with wearable devices such as VR/AR helmet and glasses.
The learned neural proposals generalize to occurrences of common structural motifs across different models, allowing for the construction of a library of learned inference primitives that can accelerate inference on unseen models with no model-specific training required.
To fully explore the local and global properties, in this paper, we propose a novel fully convolutional network, named as CoupleNet, to couple the global structure with local parts for object detection.
Ranked #6 on Object Detection on PASCAL VOC 2007
We explore deep reinforcement learning methods for multi-agent domains.
Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency, but it cannot well deal with the large scale target appearance variations due to its data-independent random projection matrix that results in less discriminative features.
no code implementations • 9 Feb 2015 • David Allouche, Christian Bessiere, Patrice Boizumault, Simon de Givry, Patricia Gutierrez, Jimmy H. M. Lee, Kam Lun Leung, Samir Loudni, Jean-Philippe Métivier, Thomas Schiex, Yi Wu
A global cost function is called tractable projection-safe when applying an EPT to it is tractable and does not break the tractability property.
In this paper we present that, even without offline training with a large amount of auxiliary data, simple two-layer convolutional networks can be powerful enough to develop a robust representation for visual tracking.
In contrast, for analyses of update rules and sparsity properties of local and global solutions, as well as extensions to more general likelihood models, we can leverage coefficient-space techniques developed for Type I and apply them to Type II.