Discovering the causality from observational data is a crucial task in various scientific domains. With increasing awareness of privacy, data are not allowed to be exposed, and it is very hard to learn causal graphs from dispersed data, since these data may have different distributions. In this paper, we propose a federated causal discovery strategy (FedCausal) to learn the unified global causal graph from decentralized heterogeneous data. We design a global optimization formula to naturally aggregate the causal graphs from client data and constrain the acyclicity of the global graph without exposing local data. Unlike other federated causal learning algorithms, FedCausal unifies the local and global optimizations into a complete directed acyclic graph (DAG) learning process with a flexible optimization objective. We prove that this optimization objective has a high interpretability and can adaptively handle homogeneous and heterogeneous data. Experimental results on synthetic and real datasets show that FedCausal can effectively deal with non-independently and identically distributed (non-iid) data and has a superior performance.

Learning directed acyclic graph (DAG) that describes the causality of observed data is a very challenging but important task. Due to the limited quantity and quality of observed data, and non-identifiability of causal graph, it is almost impossible to infer a single precise DAG. Some methods approximate the posterior distribution of DAGs to explore the DAG space via Markov chain Monte Carlo (MCMC), but the DAG space is over the nature of super-exponential growth, accurately characterizing the whole distribution over DAGs is very intractable. In this paper, we propose Reinforcement Causal Structure Learning on Order Graph (RCL-OG) that uses order graph instead of MCMC to model different DAG topological orderings and to reduce the problem size. RCL-OG first defines reinforcement learning with a new reward mechanism to approximate the posterior distribution of orderings in an efficacy way, and uses deep Q-learning to update and transfer rewards between nodes. Next, it obtains the probability transition model of nodes on order graph, and computes the posterior probability of different orderings. In this way, we can sample on this model to obtain the ordering with high probability. Experiments on synthetic and benchmark datasets show that RCL-OG provides accurate posterior probability approximation and achieves better results than competitive causal discovery algorithms.

Discovery the causal structure graph among a set of variables is a fundamental but difficult task in many empirical sciences. Reinforcement learning based causal discovery from observed data achieves prominent results. However, previous algorithms lack interpretability and efficiency, and ignore the prior knowledge of causal structure. To solve these problems, we propose GARL that leverages graph attention network to embed the structure information and the prior knowledge, and reinforcement learning to search the variable ordering with the best score. GARL takes the structure information and prior knowledge as the computational skeleton of attention to obtain the embedded representation of variables, and then generates variable orderings through the designed ordering model. In addition, the structure information is used to form the DAG corresponding to the variable ordering, which reduces the computational difficulty and improves the efficiency. GARL generates DAGs in the reinforcement learning framework, and uses the score of DAG as the reward to optimize the network structure to search the DAG with the best score. Experimental results on synthetic and real datasets show that our GARL has obvious advantages in multi-node operation efficiency, and competitive results with competitive baselines.

Although many soft robots, capable of crawling or climbing, have been well developed, integrating multimodal locomotion into a soft robot for transitioning between crawling and climbing still remains elusive. In this work, we present a class of inchworm-inspired multimodal soft crawling-climbing robots (SCCRs) that can achieve crawling, climbing, and transitioning between horizontal and vertical planes. Inspired by the inchworm’s multimodal locomotion, which depends on the “$\Omega$” deformation of the body and controllable friction force of feet, we develop the SCCR by 1) three pneumatic artificial muscles based body designed to produce “$\Omega$” deformation; 2) two negative pressure suckers adopted to generate controllable friction forces. Then a simplified kinematic model is developed to characterize the kinematic features of the SCCRs. Lastly, a control strategy is proposed to synchronously control the “$\Omega$” deformation and sucker friction forces for multimodal locomotion. The experimental results demonstrate that the SCCR can move at a maximum speed of 21 mm/s (0.11 body length/s) on horizontal planes and 15 mm/s (0.079 body length/s) on vertical walls. Furthermore, the SCCR can work in confined spaces, carry a payload of 500 g (about 15 times the self-weight) on horizontal planes or 20 g on vertical walls, and move in aquatic environments.

Shansong Yang, Weiming Lu, Dezhi Yang, Liang Yao, Baogang Wei. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.