Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources

Pre-trained language models (PLMs) have established the new paradigm in the field of NLP. For more powerful PLMs, one of the most popular and successful way is to continuously scale up sizes of the models and the pre-training corpora. These large corpora are generally obtained by converging smaller ones from multiple sources, they are thus growing increasingly diverse. However, the side-effects of these colossal converged corpora remain understudied. In this paper, we identify the disadvantage of heterogeneous corpora from multiple sources for pre-training PLMs. Towards coordinated pre-training on diverse corpora, we further propose source prompts (SP), which explicitly prompt the model of the data source at the pre-training and fine-tuning stages. Results of extensive experiments demonstrate that PLMs pre-trained with SP on diverse corpora gain significant improvement in various downstream tasks.

Robotic Assembly Control Reconfiguration Based on Transfer Reinforcement Learning for Objects with Different Geometric Features

Robotic force-based compliance control is a preferred approach to achieve high-precision assembly tasks. When the geometric features of assembly objects are asymmetric or irregular, reinforcement learning (RL) agents are gradually incorporated into the compliance controller to adapt to complex force-pose mapping which is hard to model analytically. Since force-pose mapping is strongly dependent on geometric features, a compliance controller is only optimal for current geometric features. To reduce the learning cost of assembly objects with different geometric features, this paper is devoted to answering how to reconfigure existing controllers for new assembly objects with different geometric features. In this paper, model-based parameters are first reconfigured based on the proposed Equivalent Theory of Compliance Law (ETCL). Then the RL agent is transferred based on the proposed Weighted Dimensional Policy Distillation (WDPD) method. The experiment results demonstrate that the control reconfiguration method costs less time and achieves better control performance, which confirms the validity of proposed methods.

Local Connection Reinforcement Learning Method for Efficient Control of Robotic Peg-in-Hole Assembly

Traditional control methods of robotic peg-in-hole assembly rely on complex contact state analysis. Reinforcement learning (RL) is gradually becoming a preferred method of controlling robotic peg-in-hole assembly tasks. However, the training process of RL is quite time-consuming because RL methods are always globally connected, which means all state components are assumed to be the input of policies for all action components, thus increasing action space and state space to be explored. In this paper, we first define continuous space serialized Shapley value (CS3) and construct a connection graph to clarify the correlativity of action components on state components. Then we propose a local connection reinforcement learning (LCRL) method based on the connection graph, which eliminates the influence of irrelevant state components on the selection of action components. The simulation and experiment results demonstrate that the control strategy obtained through LCRL method improves the stability and rapidity of the control process. LCRL method will enhance the data-efficiency and increase the final reward of the training process.

Progressive extension of reinforcement learning action dimension for asymmetric assembly tasks

Reinforcement learning (RL) is always the preferred embodiment to construct the control strategy of complex tasks, like asymmetric assembly tasks. However, the convergence speed of reinforcement learning severely restricts its practical application. In this paper, the convergence is first accelerated by combining RL and compliance control. Then a completely innovative progressive extension of action dimension (PEAD) mechanism is proposed to optimize the convergence of RL algorithms. The PEAD method is verified in DDPG and PPO. The results demonstrate the PEAD method will enhance the data-efficiency and time-efficiency of RL algorithms as well as increase the stable reward, which provides more potential for the application of RL.

LAW: Learning to Auto Weight

Example weighting algorithm is an effective solution to the training bias problem. However, typical methods are usually limited to human knowledge and require laborious tuning of hyperparameters. In this study, we propose a novel example weighting framework called Learning to Auto Weight (LAW), which can learn weighting policy from data adaptively based on reinforcement learning (RL). To shrink the huge searching space in a complete training process, we divide the training procedure consisting of numerous iterations into a small number of stages, and then search a low-deformational continuous vector as action, which determines the weight of each sample. To make training more efficient, we make an innovative design of the reward to remove randomness during the RL process. Experimental results demonstrate the superiority of weighting policy explored by LAW over standard training pipeline. Especially, compared with baselines, LAW can find a better weighting schedule which achieves higher accuracy in the origin CIFAR dataset, and over 10% higher in accuracy on the contaminated CIFAR dataset with 30% label noises. Our code will be released soon.

Fast Skill Learning for Variable Compliance Robotic Assembly

The robotic assembly represents a group of benchmark problems for reinforcement learning and variable compliance control that features sophisticated contact manipulation. One of the key challenges in applying reinforcement learning to physical robot is the sample complexity, the requirement of large amounts of experience for learning. We mitigate this sample complexity problem by incorporating an iteratively refitted model into the learning process through model-guided exploration. Yet, fitting a local model of the physical environment is of major difficulties. In this work, a Kalman filter is used to combine the adaptive linear dynamics with a coarse prior model from analytical description, and proves to give more accurate predictions than the existing method. Experimental results show that the proposed model fitting strategy can be incorporated into a model predictive controller to generate good exploration behaviors for learning acceleration, while preserving the benefits of model-free reinforcement learning for uncertain environments. In addition to the sample complexity, the inevitable robot overloaded during operation also tends to limit the learning efficiency. To address this problem, we present a method to restrict the largest possible potential energy in the compliance control system and therefore keep the contact force within the legitimate range.

TGE-PS: Text-driven Graph Embedding with Pairs Sampling

In graphs with rich text information, constructing expressive graph representations requires incorporating textual information with structural information. Graph embedding models are becoming more and more popular in representing graphs, yet they are faced with two issues: sampling efficiency and text utilization. Through analyzing existing models, we find their training objectives are composed of pairwise proximities, and there are large amounts of redundant node pairs in Random Walk-based methods. Besides, inferring graph structures directly from texts (also known as zero-shot scenario) is a problem that requires higher text utilization. To solve these problems, we propose a novel Text-driven Graph Embedding with Pairs Sampling (TGE-PS) framework. TGE-PS uses Pairs Sampling (PS) to generate training samples which reduces ~99% training samples and is competitive compared to Random Walk. TGE-PS uses Text-driven Graph Embedding (TGE) which adopts word- and character-level embeddings to generate node embeddings. We evaluate TGE-PS on several real-world datasets, and experimental results demonstrate that TGE-PS produces state-of-the-art results in traditional and zero-shot link prediction tasks.

Label-aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition

We study the problem of named entity recognition (NER) from electronic medical records, which is one of the most fundamental and critical problems for medical text mining. Medical records which are written by clinicians from different specialties usually contain quite different terminologies and writing styles. The difference of specialties and the cost of human annotation makes it particularly difficult to train a universal medical NER system. In this paper, we propose a label-aware double transfer learning framework (La-DTL) for cross-specialty NER, so that a medical NER system designed for one specialty could be conveniently applied to another one with minimal annotation efforts. The transferability is guaranteed by two components: (i) we propose label-aware MMD for feature representation transfer, and (ii) we perform parameter transfer with a theoretical upper bound which is also label aware. We conduct extensive experiments on 12 cross-specialty NER tasks. The experimental results demonstrate that La-DTL provides consistent accuracy improvement over strong baselines. Besides, the promising experimental results on non-medical NER scenarios indicate that La-DTL is potential to be seamlessly adapted to a wide range of NER tasks.