Reinforcement learning (RL) excels in applications such as video games and robotics, but ensuring safety and stability remains challenging when using RL to control real-world systems where using model-free algorithms suffering from low sample efficiency might be prohibitive. This paper first provides safety and stability definitions for the RL system, and then introduces a Neural ordinary differential equations-based Lyapunov-Barrier Actor-Critic (NLBAC) framework that leverages Neural Ordinary Differential Equations (NODEs) to approximate system dynamics and integrates the Control Barrier Function (CBF) and Control Lyapunov Function (CLF) frameworks with the actor-critic method to assist in maintaining the safety and stability for the system. Within this framework, we employ the augmented Lagrangian method to update the RL-based controller parameters. Additionally, we introduce an extra backup controller in situations where CBF constraints for safety and the CLF constraint for stability cannot be satisfied simultaneously. Simulation results demonstrate that the framework leads the system to approach the desired state and allows fewer violations of safety constraints with better sample efficiency compared to other methods.
相關內容
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling rehearsal examples from a generative model. Such an approach contradicts buffer-based approaches where sampling strategy plays an important role. We propose to bridge this gap by integrating diffusion models with classifier guidance techniques to produce rehearsal examples specifically targeting information forgotten by a continuously trained model. This approach enables the generation of samples from preceding task distributions, which are more likely to be misclassified in the context of recently encountered classes. Our experimental results show that GUIDE significantly reduces catastrophic forgetting, outperforming conventional random sampling approaches and surpassing recent state-of-the-art methods in continual learning with generative replay.
Deep reinforcement learning excels in numerous large-scale practical applications. However, existing performance analyses ignores the unique characteristics of continuous-time control problems, is unable to directly estimate the generalization error of the Bellman optimal loss and require a boundedness assumption. Our work focuses on continuous-time control problems and proposes a method that is applicable to all such problems where the transition function satisfies semi-group and Lipschitz properties. Under this method, we can directly analyze the \emph{a priori} generalization error of the Bellman optimal loss. The core of this method lies in two transformations of the loss function. To complete the transformation, we propose a decomposition method for the maximum operator. Additionally, this analysis method does not require a boundedness assumption. Finally, we obtain an \emph{a priori} generalization error without the curse of dimensionality.
Visual imitation learning has achieved impressive progress in learning unimanual manipulation tasks from a small set of visual observations, thanks to the latest advances in computer vision. However, learning bimanual coordination strategies and complex object relations from bimanual visual demonstrations, as well as generalizing them to categorical objects in novel cluttered scenes remain unsolved challenges. In this paper, we extend our previous work on keypoints-based visual imitation learning (\mbox{K-VIL})~\cite{gao_kvil_2023} to bimanual manipulation tasks. The proposed Bi-KVIL jointly extracts so-called \emph{Hybrid Master-Slave Relationships} (HMSR) among objects and hands, bimanual coordination strategies, and sub-symbolic task representations. Our bimanual task representation is object-centric, embodiment-independent, and viewpoint-invariant, thus generalizing well to categorical objects in novel scenes. We evaluate our approach in various real-world applications, showcasing its ability to learn fine-grained bimanual manipulation tasks from a small number of human demonstration videos. Videos and source code are available at //sites.google.com/view/bi-kvil.
Federated learning is a promising framework to train neural networks with widely distributed data. However, performance degrades heavily with heterogeneously distributed data. Recent work has shown this is due to the final layer of the network being most prone to local bias, some finding success freezing the final layer as an orthogonal classifier. We investigate the training dynamics of the classifier by applying SVD to the weights motivated by the observation that freezing weights results in constant singular values. We find that there are differences when training in IID and non-IID settings. Based on this finding, we introduce two regularization terms for local training to continuously emulate IID settings: (1) variance in the dimension-wise probability distribution of the classifier and (2) hyperspherical uniformity of representations of the encoder. These regularizations promote local models to act as if it were in an IID setting regardless of the local data distribution, thus offsetting proneness to bias while being flexible to the data. On extensive experiments in both label-shift and feature-shift settings, we verify that our method achieves highest performance by a large margin especially in highly non-IID cases in addition to being scalable to larger models and datasets.
Recommender systems are effective tools for mitigating information overload and have seen extensive applications across various domains. However, the single focus on utility goals proves to be inadequate in addressing real-world concerns, leading to increasing attention to fairness-aware and diversity-aware recommender systems. While most existing studies explore fairness and diversity independently, we identify strong connections between these two domains. In this survey, we first discuss each of them individually and then dive into their connections. Additionally, motivated by the concepts of user-level and item-level fairness, we broaden the understanding of diversity to encompass not only the item level but also the user level. With this expanded perspective on user and item-level diversity, we re-interpret fairness studies from the viewpoint of diversity. This fresh perspective enhances our understanding of fairness-related work and paves the way for potential future research directions. Papers discussed in this survey along with public code links are available at //github.com/YuyingZhao/Awesome-Fairness-and-Diversity-Papers-in-Recommender-Systems .
The anchor-document data derived from web graphs offers a wealth of paired information for training dense retrieval models in an unsupervised manner. However, the presence of inherent noise invariably compromises the robustness of training dense retrieval models, consequently hurting the performance. In this paper, we introduce WebDRO, an efficient approach for clustering the web graph data and optimizing group weights to enhance the robustness of the pretraining process of dense retrieval models on web graphs. Initially, we build an embedding model for clustering anchor-document pairs. Specifically, we contrastively train the embedding model for link prediction, which guides the embedding model in capturing the inherent document features behind the web graph links. Subsequently, we employ the group distributional robust optimization to recalibrate the weights across different clusters of anchor-document pairs during training dense retrieval models, directing the model to assign higher weights to clusters with higher loss and focus more on worst-case scenarios. Our experiments conducted on MS MARCO and BEIR demonstrate that our method can effectively improve retrieval performance in unsupervised training settings. Further analysis confirms the stability and validity of group weights learned by WebDRO. All codes will be released via GitHub.
Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which an attacker injects poisoned inputs into the pre-training dataset so the encoder is backdoored. However, existing DPBAs achieve limited effectiveness. In this work, we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL. CorruptEncoder introduces a new attack strategy to create poisoned inputs and uses a theory-guided method to maximize attack effectiveness. Our experiments show that CorruptEncoder substantially outperforms existing DPBAs. In particular, CorruptEncoder is the first DPBA that achieves more than 90% attack success rates with only a few (3) reference images and a small poisoning ratio 0.5%. Moreover, we also propose a defense, called localized cropping, to defend against DPBAs. Our results show that our defense can reduce the effectiveness of DPBAs, but it sacrifices the utility of the encoder, highlighting the need for new defenses.
Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs. Although many methods and applications have been developed for FL, several critical challenges for practical FL systems remain unaddressed. This paper provides an outlook on FL development, categorized into five emerging directions of FL, namely algorithm foundation, personalization, hardware and security constraints, lifelong learning, and nonstandard data. Our unique perspectives are backed by practical observations from large-scale federated systems for edge devices.
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classication
Multiple instance learning (MIL) is a powerful tool to solve the weakly supervised classification in whole slide image (WSI) based pathology diagnosis. However, the current MIL methods are usually based on independent and identical distribution hypothesis, thus neglect the correlation among different instances. To address this problem, we proposed a new framework, called correlated MIL, and provided a proof for convergence. Based on this framework, we devised a Transformer based MIL (TransMIL), which explored both morphological and spatial information. The proposed TransMIL can effectively deal with unbalanced/balanced and binary/multiple classification with great visualization and interpretability. We conducted various experiments for three different computational pathology problems and achieved better performance and faster convergence compared with state-of-the-art methods. The test AUC for the binary tumor classification can be up to 93.09% over CAMELYON16 dataset. And the AUC over the cancer subtypes classification can be up to 96.03% and 98.82% over TCGA-NSCLC dataset and TCGA-RCC dataset, respectively.
Recently, ensemble has been applied to deep metric learning to yield state-of-the-art results. Deep metric learning aims to learn deep neural networks for feature embeddings, distances of which satisfy given constraint. In deep metric learning, ensemble takes average of distances learned by multiple learners. As one important aspect of ensemble, the learners should be diverse in their feature embeddings. To this end, we propose an attention-based ensemble, which uses multiple attention masks, so that each learner can attend to different parts of the object. We also propose a divergence loss, which encourages diversity among the learners. The proposed method is applied to the standard benchmarks of deep metric learning and experimental results show that it outperforms the state-of-the-art methods by a significant margin on image retrieval tasks.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191