Many real-world domains require safe decision making in uncertain environments. In this work, we introduce a deep reinforcement learning framework for approaching this important problem. We consider a distribution over transition models, and apply a risk-averse perspective towards model uncertainty through the use of coherent distortion risk measures. We provide robustness guarantees for this framework by showing it is equivalent to a specific class of distributionally robust safe reinforcement learning problems. Unlike existing approaches to robustness in deep reinforcement learning, however, our formulation does not involve minimax optimization. This leads to an efficient, model-free implementation of our approach that only requires standard data collection from a single training environment. In experiments on continuous control tasks with safety constraints, we demonstrate that our framework produces robust performance and safety at deployment time across a range of perturbed test environments.
相關內容
Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An efficient network should skip iterations when the flow improvement is limited. In this paper, we develop a Context-Aware Iteration Policy Network for efficient optical flow estimation, which determines the optimal number of iterations per sample. The policy network achieves this by learning contextual information to realize whether flow improvement is bottlenecked or minimal. On the one hand, we use iteration embedding and historical hidden cell, which include previous iterations information, to convey how flow has changed from previous iterations. On the other hand, we use the incremental loss to make the policy network implicitly perceive the magnitude of optical flow improvement in the subsequent iteration. Furthermore, the computational complexity in our dynamic network is controllable, allowing us to satisfy various resource preferences with a single trained model. Our policy network can be easily integrated into state-of-the-art optical flow networks. Extensive experiments show that our method maintains performance while reducing FLOPs by about 40%/20% for the Sintel/KITTI datasets.
Deep neural networks (DNNs) that incorporated lifelong sequential modeling (LSM) have brought great success to recommendation systems in various social media platforms. While continuous improvements have been made in domain-specific LSM, limited work has been done in cross-domain LSM, which considers modeling of lifelong sequences of both target domain and source domain. In this paper, we propose Lifelong Cross Network (LCN) to incorporate cross-domain LSM to improve the click-through rate (CTR) prediction in the target domain. The proposed LCN contains a LifeLong Attention Pyramid (LAP) module that comprises of three levels of cascaded attentions to effectively extract interest representations with respect to the candidate item from lifelong sequences. We also propose Cross Representation Production (CRP) module to enforce additional supervision on the learning and alignment of cross-domain representations so that they can be better reused on learning of the CTR prediction in the target domain. We conducted extensive experiments on WeChat Channels industrial dataset as well as on benchmark dataset. Results have revealed that the proposed LCN outperforms existing work in terms of both prediction accuracy and online performance.
Time series forecasting (TSF) holds significant importance in modern society, spanning numerous domains. Previous representation learning-based TSF algorithms typically embrace a contrastive learning paradigm featuring segregated trend-periodicity representations. Yet, these methodologies disregard the inherent high-impact noise embedded within time series data, resulting in representation inaccuracies and seriously demoting the forecasting performance. To address this issue, we propose CLeaRForecast, a novel contrastive learning framework to learn high-purity time series representations with proposed sample, feature, and architecture purifying methods. More specifically, to avoid more noise adding caused by the transformations of original samples (series), transformations are respectively applied for trendy and periodic parts to provide better positive samples with obviously less noise. Moreover, we introduce a channel independent training manner to mitigate noise originating from unrelated variables in the multivariate series. By employing a streamlined deep-learning backbone and a comprehensive global contrastive loss function, we prevent noise introduction due to redundant or uneven learning of periodicity and trend. Experimental results show the superior performance of CLeaRForecast in various downstream TSF tasks.
In this paper, we delve into the advancement of domain-specific Large Language Models (LLMs) with a focus on their application in software development. We introduce DevAssistLlama, a model developed through instruction tuning, to assist developers in processing software-related natural language queries. This model, a variant of instruction tuned LLM, is particularly adept at handling intricate technical documentation, enhancing developer capability in software specific tasks. The creation of DevAssistLlama involved constructing an extensive instruction dataset from various software systems, enabling effective handling of Named Entity Recognition (NER), Relation Extraction (RE), and Link Prediction (LP). Our results demonstrate DevAssistLlama's superior capabilities in these tasks, in comparison with other models including ChatGPT. This research not only highlights the potential of specialized LLMs in software development also the pioneer LLM for this domain.
Nanopore sequencing, superior to other sequencing technologies for DNA storage in multiple aspects, has recently attracted considerable attention. Its high error rates, however, demand thorough research on practical and efficient coding schemes to enable accurate recovery of stored data. To this end, we consider a simplified model of a nanopore sequencer inspired by Mao \emph{et al.}, incorporating intersymbol interference and measurement noise. Essentially, our channel model passes a sliding window of length \(\ell\) over a \(q\)-ary input sequence that outputs the \textit{composition} of the enclosed \(\ell\) bits and shifts by \(\delta\) positions with each time step. In this context, the composition of a \(q\)-ary vector $\bfx$ specifies the number of occurrences in \(\bfx\) of each symbol in \(\lbrace 0,1,\ldots, q-1\rbrace\). The resulting compositions vector, termed the \emph{read vector}, may also be corrupted by \(t\) substitution errors. By employing graph-theoretic techniques, we deduce that for \(\delta=1\), at least \(\log \log n\) symbols of redundancy are required to correct a single (\(t=1\)) substitution. Finally, for \(\ell \geq 3\), we exploit some inherent characteristics of read vectors to arrive at an error-correcting code that is of optimal redundancy up to a (small) additive constant for this setting. This construction is also found to be optimal for the case of reconstruction from two noisy read vectors.
While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from causality toward RL. In particular, we divide existing CRL approaches into two categories according to whether their causality-based information is given in advance or not. We further analyze each category in terms of the formalization of different models, ranging from the Markov Decision Process (MDP), Partially Observed Markov Decision Process (POMDP), Multi-Arm Bandits (MAB), and Dynamic Treatment Regime (DTR). Moreover, we summarize the evaluation matrices and open sources while we discuss emerging applications, along with promising prospects for the future development of CRL.
Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph representation. However, there is an inherent gap between self-supervised tasks and downstream tasks in terms of optimization objective and training data. Conventional pre-training methods may be not effective enough on knowledge transfer since they do not make any adaptation for downstream tasks. To solve such problems, we propose a new transfer learning paradigm on GNNs which could effectively leverage self-supervised tasks as auxiliary tasks to help the target task. Our methods would adaptively select and combine different auxiliary tasks with the target task in the fine-tuning stage. We design an adaptive auxiliary loss weighting model to learn the weights of auxiliary tasks by quantifying the consistency between auxiliary tasks and the target task. In addition, we learn the weighting model through meta-learning. Our methods can be applied to various transfer learning approaches, it performs well not only in multi-task learning but also in pre-training and fine-tuning. Comprehensive experiments on multiple downstream tasks demonstrate that the proposed methods can effectively combine auxiliary tasks with the target task and significantly improve the performance compared to state-of-the-art methods.
In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. However, the trained model cannot produce a highly discriminative feature representation for the target domain because the training data is dominated by labeled samples from the source domain. This could lead to disconnection between the labeled and unlabeled target samples as well as misalignment between unlabeled target samples and the source domain. In this paper, we propose a novel approach called Cross-domain Adaptive Clustering to address this problem. To achieve both inter-domain and intra-domain adaptation, we first introduce an adversarial adaptive clustering loss to group features of unlabeled target data into clusters and perform cluster-wise feature alignment across the source and target domains. We further apply pseudo labeling to unlabeled samples in the target domain and retain pseudo-labels with high confidence. Pseudo labeling expands the number of ``labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning. Extensive experiments on benchmark datasets, including DomainNet, Office-Home and Office, demonstrate that our proposed approach achieves the state-of-the-art performance in semi-supervised domain adaptation.
User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total time of the conversation. In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems. Our experiments demonstrate that (1) human annotators have high agreement on assessing utterance-level engagement scores; (2) conversation-level engagement scores can be predicted from properly aggregated utterance-level engagement scores. Furthermore, we show that the utterance-level engagement scores can be learned from data. These scores can improve automatic evaluation metrics for open-domain dialogue systems, as shown by correlation with human judgements. This suggests that predictive engagement can be used as a real-time feedback for training better dialogue models.
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images. To achieve diversity, we propose to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and a domain-specific attribute space. Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time. To handle unpaired training data, we introduce a novel cross-cycle consistency loss based on disentangled representations. Qualitative results show that our model can generate diverse and realistic images on a wide range of tasks without paired training data. For quantitative comparisons, we measure realism with user study and diversity with a perceptual distance metric. We apply the proposed model to domain adaptation and show competitive performance when compared to the state-of-the-art on the MNIST-M and the LineMod datasets.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191