In this paper, we propose a distributed zeroth-order policy optimization method for Multi-Agent Reinforcement Learning (MARL). Existing MARL algorithms often assume that every agent can observe the states and actions of all the other agents in the network. This can be impractical in large-scale problems, where sharing the state and action information with multi-hop neighbors may incur significant communication overhead. The advantage of the proposed zeroth-order policy optimization method is that it allows the agents to compute the local policy gradients needed to update their local policy functions using local estimates of the global accumulated rewards that depend on partial state and action information only and can be obtained using consensus. Specifically, to calculate the local policy gradients, we develop a new distributed zeroth-order policy gradient estimator that relies on one-point residual-feedback which, compared to existing zeroth-order estimators that also rely on one-point feedback, significantly reduces the variance of the policy gradient estimates improving, in this way, the learning performance. We show that the proposed distributed zeroth-order policy optimization method with constant stepsize converges to a neighborhood of the global optimal policy that depends on the number of consensus steps used to calculate the local estimates of the global accumulated rewards. Moreover, we provide numerical experiments that demonstrate that our new zeroth-order policy gradient estimator is more sample-efficient compared to other existing one-point estimators.
Many existing zeroth-order optimization (ZO) algorithms adopt two-point feedback schemes due to their fast convergence rate compared to one-point feedback schemes. However, two-point schemes require two evaluations of the objective function at each iteration, which can be impractical in applications where the data are not all available a priori, e.g., in online optimization. In this paper, we propose a novel one-point feedback scheme that queries the function value only once at each iteration and estimates the gradient using the residual between two consecutive feedback points. When optimizing a deterministic Lipschitz function, we show that the query complexity of ZO with the proposed one-point residual feedback matches that of ZO with the existing two-point feedback schemes. Moreover, the query complexity of the proposed algorithm can be improved when the objective function has Lipschitz gradient. Then, for stochastic bandit optimization problems, we show that ZO with one-point residual feedback achieves the same convergence rate as that of ZO with two-point feedback with uncontrollable data samples. We demonstrate the effectiveness of the proposed one-point residual feedback via extensive numerical experiments.
Existing works on KG-to-text generation take as input a few RDF triples or key-value pairs conveying the knowledge of some entities to generate a natural language description. Existing datasets, such as WikiBIO, WebNLG, and E2E, basically have a good alignment between an input triple/pair set and its output text. However in practice, the input knowledge could be more than enough, because the output description may only want to cover the most significant knowledge. In this paper, we introduce a large-scale and challenging dataset to facilitate the study of such practical scenario in KG-to-text. Our dataset involves exploring large knowledge graphs (KG) to retrieve abundant knowledge of various types of main entities, which makes the current graph-to-sequence models severely suffered from the problems of information loss and parameter explosion while generating the description text. We address these challenges by proposing a multi-graph structure that is able to represent the original graph information more comprehensively. Furthermore, we also incorporate aggregation methods that learn to ensemble the rich graph information. Extensive experiments demonstrate the effectiveness of our model architecture.
One of the most popular paradigms of applying large, pre-trained NLP models such as BERT is to fine-tune it on a smaller dataset. However, one challenge remains as the fine-tuned model often overfits on smaller datasets. A symptom of this phenomenon is that irrelevant words in the sentences, even when they are obvious to humans, can substantially degrade the performance of these fine-tuned BERT models. In this paper, we propose a novel technique, called Self-Supervised Attention (SSA) to help facilitate this generalization challenge. Specifically, SSA automatically generates weak, token-level attention labels iteratively by "probing" the fine-tuned model from the previous iteration. We investigate two different ways of integrating SSA into BERT and propose a hybrid approach to combine their benefits. Empirically, on a variety of public datasets, we illustrate significant performance improvement using our SSA-enhanced BERT model.
Satirical news detection is an important yet challenging task to prevent spread of misinformation. Many feature based and end-to-end neural nets based satirical news detection systems have been proposed and delivered promising results. Existing approaches explore comprehensive word features from satirical news articles, but lack semantic metrics using word vectors for tweet form satirical news. Moreover, the vagueness of satire and news parody determines that a news tweet can hardly be classified with a binary decision, that is, satirical or legitimate. To address these issues, we collect satirical and legitimate news tweets, and propose a semantic feature based approach. Features are extracted by exploring inconsistencies in phrases, entities, and between main and relative clauses. We apply game-theoretic rough set model to detect satirical news, in which probabilistic thresholds are derived by game equilibrium and repetition learning mechanism. Experimental results on the collected dataset show the robustness and improvement of the proposed approach compared with Pawlak rough set model and SVM.
Since the PointNet was proposed, deep learning on point cloud has been the concentration of intense 3D research. However, existing point-based methods usually are not adequate to extract the local features and the spatial pattern of a point cloud for further shape understanding. This paper presents an end-to-end framework, SK-Net, to jointly optimize the inference of spatial keypoint with the learning of feature representation of a point cloud for a specific point cloud task. One key process of SK-Net is the generation of spatial keypoints (Skeypoints). It is jointly conducted by two proposed regulating losses and a task objective function without knowledge of Skeypoint location annotations and proposals. Specifically, our Skeypoints are not sensitive to the location consistency but are acutely aware of shape. Another key process of SK-Net is the extraction of the local structure of Skeypoints (detail feature) and the local spatial pattern of normalized Skeypoints (pattern feature). This process generates a comprehensive representation, pattern-detail (PD) feature, which comprises the local detail information of a point cloud and reveals its spatial pattern through the part district reconstruction on normalized Skeypoints. Consequently, our network is prompted to effectively understand the correlation between different regions of a point cloud and integrate contextual information of the point cloud. In point cloud tasks, such as classification and segmentation, our proposed method performs better than or comparable with the state-of-the-art approaches. We also present an ablation study to demonstrate the advantages of SK-Net.
Unstructured data often has latent component structure, such as the objects in an image of a scene. In these situations, the relevant latent structure is an unordered collection or \emph{set}. However, learning such representations directly from data is difficult due to the discrete and unordered structure. Here, we develop a framework for differentiable learning of set-structured latent representations. We show how to use this framework to naturally decompose data such as images into sets of interpretable and meaningful components and demonstrate how existing techniques cannot properly disentangle relevant structure. We also show how to extend our methodology to downstream tasks such as set matching, which uses set-specific operations. Our code is available at https://github.com/CUVL/SSLR.
In this paper, we study a transfer reinforcement learning problem where the state transitions and rewards are affected by the environmental context. Specifically, we consider a demonstrator agent that has access to a context-aware policy and can generate transition and reward data based on that policy. These data constitute the experience of the demonstrator. Then, the goal is to transfer this experience, excluding the underlying contextual information, to a learner agent that does not have access to the environmental context, so that they can learn a control policy using fewer samples. It is well known that, disregarding the causal effect of the contextual information, can introduce bias in the transition and reward models estimated by the learner, resulting in a learned suboptimal policy. To address this challenge, in this paper, we develop a method to obtain causal bounds on the transition and reward functions using the demonstrator's data, which we then use to obtain causal bounds on the value functions. Using these value function bounds, we propose new Q learning and UCB-Q learning algorithms that converge to the true value function without bias. We provide numerical experiments for robot motion planning problems that validate the proposed value function bounds and demonstrate that the proposed algorithms can effectively make use of the data from the demonstrator to accelerate the learning process of the learner.
Change detection is an important problem in vision field, especially for aerial images. However, most works focus on traditional change detection, i.e., where changes happen, without considering the change type information, i.e., what changes happen. Although a few works have tried to apply semantic information to traditional change detection, they either only give the label of emerging objects without taking the change type into consideration, or set some kinds of change subjectively without specifying semantic information. To make use of semantic information and analyze change types comprehensively, we propose a new task called semantic change pattern analysis for aerial images. Given a pair of co-registered aerial images, the task requires a result including both where and what changes happen. We then describe the metric adopted for the task, which is clean and interpretable. We further provide the first well-annotated aerial image dataset for this task. Extensive baseline experiments are conducted as reference for following works. The aim of this work is to explore high-level information based on change detection and facilitate the development of this field with the publicly available dataset.