The Design and Realization of Multi-agent Obstacle Avoidance based on Reinforcement Learning

Intelligence agents and multi-agent systems play important roles in scenes like the control system of grouped drones, and multi-agent navigation and obstacle avoidance which is the foundational function of advanced application has great importance. In multi-agent navigation and obstacle avoidance tasks, the decision-making interactions and dynamic changes of agents are difficult for traditional route planning algorithms or reinforcement learning algorithms with the increased complexity of the environment. The classical multi-agent reinforcement learning algorithm, Multi-agent deep deterministic policy gradient(MADDPG), solved precedent algorithms' problems of having unstationary training process and unable to deal with environment randomness. However, MADDPG ignored the temporal message hidden beneath agents' interaction with the environment. Besides, due to its CTDE technique which let each agent's critic network to calculate over all agents' action and the whole environment information, it lacks ability to scale to larger amount of agents. To deal with MADDPG's ignorance of the temporal information of the data, this article proposes a new algorithm called MADDPG-LSTMactor, which combines MADDPG with Long short term memory (LSTM). By using agent's observations of continuous timesteps as the input of its policy network, it allows the LSTM layer to process the hidden temporal message. Experimental result demonstrated that this algorithm had better performance in scenarios where the amount of agents is small. Besides, to solve MADDPG's drawback of not being efficient in scenarios where agents are too many, this article puts forward a light-weight MADDPG (MADDPG-L) algorithm, which simplifies the input of critic network. The result of experiments showed that this algorithm had better performance than MADDPG when the amount of agents was large.

Improving Radiology Summarization with Radiograph and Anatomy Prompts

The impression is crucial for the referring physicians to grasp key information since it is concluded from the findings and reasoning of radiologists. To alleviate the workload of radiologists and reduce repetitive human labor in impression writing, many researchers have focused on automatic impression generation. However, recent works on this task mainly summarize the corresponding findings and pay less attention to the radiology images. In clinical, radiographs can provide more detailed valuable observations to enhance radiologists' impression writing, especially for complicated cases. Besides, each sentence in findings usually focuses on single anatomy, so they only need to be matched to corresponding anatomical regions instead of the whole image, which is beneficial for textual and visual features alignment. Therefore, we propose a novel anatomy-enhanced multimodal model to promote impression generation. In detail, we first construct a set of rules to extract anatomies and put these prompts into each sentence to highlight anatomy characteristics. Then, two separate encoders are applied to extract features from the radiograph and findings. Afterward, we utilize a contrastive learning module to align these two representations at the overall level and use a co-attention to fuse them at the sentence level with the help of anatomy-enhanced sentence representation. Finally, the decoder takes the fused information as the input to generate impressions. The experimental results on two benchmark datasets confirm the effectiveness of the proposed method, which achieves state-of-the-art results.

FedCross: Towards Accurate Federated Learning via Multi-Model Cross Aggregation

Due to the remarkable performance in preserving data privacy for decentralized data scenarios, Federated Learning (FL) has been considered as a promising distributed machine learning paradigm to deal with data silos problems. Typically, conventional FL approaches adopts a one-to-multi training scheme, where the cloud server keeps only one single global model for all the involved clients for the purpose of model aggregation. However, this scheme suffers from inferior classification performance, since only one global model cannot always accommodate all the incompatible convergence directions of local models, resulting in a low convergence rate and classification accuracy. To address this issue, this paper presents an efficient FL framework named FedCross, which adopts a novel multi-to-multi FL training scheme based on our proposed similarity-based multi-model cross aggregation method. Unlike traditional FL methods, in each round of FL training, FedCross uses a small set of distinct intermediate models to conduct weighted fusion under the guidance of model similarities. In this way, the intermediate models used by FedCross can sufficiently respect the convergence characteristics of clients, thus leading to much fewer conflicts in tuning the convergence directions of clients. Finally, in the deployment stage, FedCross forms a global model for all the clients by performing the federated averaging on the trained immediate models.

Towards a Unified Multi-Dimensional Evaluator for Text Generation

Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency. However, automatic evaluation in NLG is still dominated by similarity-based metrics, and we lack a reliable framework for a more comprehensive evaluation of advanced models. In this paper, we propose a unified multi-dimensional evaluator UniEval for NLG. We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions. Furthermore, thanks to the unified Boolean QA format, we are able to introduce an intermediate learning phase that enables UniEval to incorporate external knowledge from multiple related tasks and gain further improvement. Experiments on three typical NLG tasks show that UniEval correlates substantially better with human judgments than existing metrics. Specifically, compared to the top-performing unified evaluators, UniEval achieves a 23% higher correlation on text summarization, and over 43% on dialogue response generation. Also, UniEval demonstrates a strong zero-shot learning ability for unseen evaluation dimensions and tasks. Source code, data and all pre-trained evaluators are available on our GitHub repository (https://github.com/maszhongming/UniEval).

Task Compass: Scaling Multi-task Pre-training with Task Prefix

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL

Exploring Interactions and Regulations in Collaborative Learning: An Interdisciplinary Multimodal Dataset

Collaborative learning is an educational approach that enhances learning through shared goals and working together. Interaction and regulation are two essential factors related to the success of collaborative learning. Since the information from various modalities can reflect the quality of collaboration, a new multimodal dataset with cognitive and emotional triggers is introduced in this paper to explore how regulations affect interactions during the collaborative process. Specifically, a learning task with intentional interventions is designed and assigned to high school students aged 15 years old (N=81) in average. Multimodal signals, including video, Kinect, audio, and physiological data, are collected and exploited to study regulations in collaborative learning in terms of individual-participant-single-modality, individual-participant-multiple-modality, and multiple-participant-multiple-modality. Analysis of annotated emotions, body gestures, and their interactions indicates that our multimodal dataset with designed treatments could effectively examine moments of regulation in collaborative learning. In addition, preliminary experiments based on baseline models suggest that the dataset provides a challenging in-the-wild scenario, which could further contribute to the fields of education and affective computing.

Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization

Warning: this paper contains model outputs exhibiting offensiveness and biases. Recently pre-trained language models (PLMs) have prospered in various natural language generation (NLG) tasks due to their ability to generate fairly fluent text. Nevertheless, these models are observed to capture and reproduce harmful contents in training corpora, typically toxic language and social biases, raising severe moral issues. Prior works on ethical NLG tackle detoxifying and debiasing separately, which is problematic since we find debiased models still exhibit toxicity while detoxified ones even exacerbate biases. To address such a challenge, we propose the first unified framework of detoxifying and debiasing called UDDIA, which jointly formalizes these two problems as rectifying the output space. We theoretically interpret our framework as learning a text distribution mixing weighted attributes. Besides, UDDIA conducts adaptive optimization of only a few parameters during decoding based on a parameter-efficient tuning schema without any training data. This leads to minimal generation quality loss and improved rectification performance with acceptable computational cost. Experimental results demonstrate that compared to several strong baselines, UDDIA achieves debiasing and detoxifying simultaneously and better balances efficiency and effectiveness, taking a further step towards practical ethical NLG.

Evaluating Fairness Without Sensitive Attributes: A Framework Using Only Auxiliary Models

Although the volume of literature and public attention on machine learning fairness has been growing significantly, in practice some tasks as basic as measuring fairness, which is the first step in studying and promoting fairness, can be challenging. This is because sensitive attributes are often unavailable due to privacy regulations. The straightforward solution is to use auxiliary models to predict the missing sensitive attributes. However, our theoretical analyses show that the estimation error of the directly measured fairness metrics is proportional to the error rates of auxiliary models' predictions. Existing works that attempt to reduce the estimation error often require strong assumptions, e.g. access to the ground-truth sensitive attributes or some form of conditional independence. In this paper, we drop those assumptions and propose a framework that uses only off-the-shelf auxiliary models. The main challenge is how to reduce the negative impact of imperfectly predicted sensitive attributes on the fairness metrics without knowing the ground-truth sensitive attributes. Inspired by the noisy label learning literature, we first derive a closed-form relationship between the directly measured fairness metrics and their corresponding ground-truth metrics. And then we estimate some key statistics (most importantly transition matrix in the noisy label literature), which we use, together with the derived relationship, to calibrate the fairness metrics. In addition, we theoretically prove the upper bound of the estimation error in our calibrated metrics and show our method can substantially decrease the estimation error especially when auxiliary models are inaccurate or the target model is highly biased. Experiments on COMPAS and CelebA validate our theoretical analyses and show our method can measure fairness significantly more accurately than baselines under favorable circumstances.

Joint Beamforming Designs for Active Reconfigurable Intelligent Surface: A Sub-Connected Array Architecture

Reconfigurable intelligent surface (RIS) is regarded as a promising technology with great potential to boost wireless networks. Affected by the "double fading" effect, however, conventional passive RIS cannot bring considerable performance improvement when users are not close enough to RIS. Recently, active RIS is introduced to combat the double fading effect by actively amplifying incident signals with the aid of integrated reflection-type amplifiers. In order to reduce the hardware cost and energy consumption due to massive active components in the conventional fully-connected active RIS, a novel hardware-and-energy efficient sub-connected active RIS architecture has been proposed recently, in which multiple reconfigurable electromagnetic elements are driven by only one amplifier. In this paper, we first develop an improved and accurate signal model for the sub-connected active RIS architecture. Then, we investigate the joint transmit precoding and RIS reflection beamforming (i.e., the reflection phase-shift and amplification coefficients) designs in multiuser multiple-input single-output (MU-MISO) communication systems. Both sum-rate maximization and power minimization problems are solved by leveraging fractional programming (FP), block coordinate descent (BCD), second-order cone programming (SOCP), alternating direction method of multipliers (ADMM), and majorization-minimization (MM) methods. Extensive simulation results verify that compared with the conventional fully-connected structure, the proposed sub-connected active RIS can significantly reduce the hardware cost and power consumption, and achieve great performance improvement when power budget at RIS is limited.

Revealing Unobservables by Deep Learning: Generative Element Extraction Networks (GEEN)

Latent variable models are crucial in scientific research, where a key variable, such as effort, ability, and belief, is unobserved in the sample but needs to be identified. This paper proposes a novel method for estimating realizations of a latent variable $X^*$ in a random sample that contains its multiple measurements. With the key assumption that the measurements are independent conditional on $X^*$, we provide sufficient conditions under which realizations of $X^*$ in the sample are locally unique in a class of deviations, which allows us to identify realizations of $X^*$. To the best of our knowledge, this paper is the first to provide such identification in observation. We then use the Kullback-Leibler distance between the two probability densities with and without the conditional independence as the loss function to train a Generative Element Extraction Networks (GEEN) that maps from the observed measurements to realizations of $X^*$ in the sample. The simulation results imply that this proposed estimator works quite well and the estimated values are highly correlated with realizations of $X^*$. Our estimator can be applied to a large class of latent variable models and we expect it will change how people deal with latent variables.