Trustworthy AI: From Principles to Practices

Fast developing artificial intelligence (AI) technology has enabled various applied systems deployed in the real world, impacting people's everyday lives. However, many current AI systems were found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection, etc., which not only degrades user experience but erodes the society's trust in all AI systems. In this review, we strive to provide AI practitioners a comprehensive guide towards building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, alignment with human values, and accountability. We then survey leading approaches in these aspects in the industry. To unify the current fragmented approaches towards trustworthy AI, we propose a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items to practitioners and societal stakeholders (e.g., researchers and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges in the future development of trustworthy AI systems, where we identify the need for paradigm shift towards comprehensive trustworthy AI systems.

DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks

Analog circuit sizing takes a significant amount of manual effort in a typical design cycle. With rapidly developing technology and tight schedules, bringing automated solutions for sizing has attracted great attention. This paper presents DNN-Opt, a Reinforcement Learning (RL) inspired Deep Neural Network (DNN) based black-box optimization framework for analog circuit sizing. The key contributions of this paper are a novel sample-efficient two-stage deep learning optimization framework leveraging RL actor-critic algorithms, and a recipe to extend it on large industrial circuits using critical device identification. Our method shows 5--30x sample efficiency compared to other black-box optimization methods both on small building blocks and on large industrial circuits with better performance metrics. To the best of our knowledge, this is the first application of DNN-based circuit sizing on industrial scale circuits.

OOWL500: Overcoming Dataset Collection Bias in the Wild

The hypothesis that image datasets gathered online "in the wild" can produce biased object recognizers, e.g. preferring professional photography or certain viewing angles, is studied. A new "in the lab" data collection infrastructure is proposed consisting of a drone which captures images as it circles around objects. Crucially, the control provided by this setup and the natural camera shake inherent to flight mitigate many biases. It's inexpensive and easily replicable nature may also potentially lead to a scalable data collection effort by the vision community. The procedure's usefulness is demonstrated by creating a dataset of Objects Obtained With fLight (OOWL). Denoted as OOWL500, it contains 120,000 images of 500 objects and is the largest "in the lab" image dataset available when both number of classes and objects per class are considered. Furthermore, it has enabled several of new insights on object recognition. First, a novel adversarial attack strategy is proposed, where image perturbations are defined in terms of semantic properties such as camera shake and pose. Indeed, experiments have shown that ImageNet has considerable amounts of pose and professional photography bias. Second, it is used to show that the augmentation of in the wild datasets, such as ImageNet, with in the lab data, such as OOWL500, can significantly decrease these biases, leading to object recognizers of improved generalization. Third, the dataset is used to study questions on "best procedures" for dataset collection. It is revealed that data augmentation with synthetic images does not suffice to eliminate in the wild datasets biases, and that camera shake and pose diversity play a more important role in object recognition robustness than previously thought.

Practical and Secure Federated Recommendation with Personalized Masks

Federated recommendation is a new notion of private distributed recommender systems. It aims to address the data silo and privacy problems altogether. Current federated recommender systems mainly utilize homomorphic encryption and differential privacy methods to protect the intermediate computational results. However, the former comes with extra communication and computation costs, the latter damages model accuracy. Neither of them could simultaneously satisfy the real-time feedback and accurate personalization requirements of recommender systems. In this paper, we proposed a new federated recommendation framework, named federated masked matrix factorization. Federated masked matrix factorization could protect the data privacy in federated recommender systems without sacrificing efficiency or efficacy. Instead of using homomorphic encryption and differential privacy, we utilize the secret sharing technique to incorporate the secure aggregation process of federated matrix factorization. Compared with homomorphic encryption, secret sharing largely speeds up the whole training process. In addition, we introduce a new idea of personalized masks and apply it in the proposed federated masked matrix factorization framework. On the one hand, personalized masks could further improve efficiency. On the other hand, personalized masks also benefit efficacy. Empirically, we show the superiority of the designed model on different real-world data sets. Besides, we also provide the privacy guarantee and discuss the extension of the personalized mask method to the general federated learning tasks.

TDM: Trustworthy Decision-Making via Interpretability Enhancement

Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust is an influential factor in determining the reliance on autonomy. However, it is not reasonable to trust systems that are beyond our comprehension, and typical machine learning and data-driven decision-making are black-box paradigms that impede interpretability. Therefore, it is critical to establish computational trustworthy decision-making mechanisms enhanced by interpretability-aware strategies. To this end, we propose a Trustworthy Decision-Making (TDM) framework, which integrates symbolic planning into sequential decision-making. The framework learns interpretable subtasks that result in a complex, higher-level composite task that can be formally evaluated using the proposed trust metric. TDM enables the subtask-level interpretability by design and converges to an optimal symbolic plan from the learned subtasks. Moreover, a TDM-based algorithm is introduced to demonstrate the unification of symbolic planning with other sequential-decision making algorithms, reaping the benefits of both. Experimental results validate the effectiveness of trust-score-based planning while improving the interpretability of subtasks.

Fedlearn-Algo: A flexible open-source privacy-preserving machine learning platform

In this paper, we present Fedlearn-Algo, an open-source privacy preserving machine learning platform. We use this platform to demonstrate our research and development results on privacy preserving machine learning algorithms. As the first batch of novel FL algorithm examples, we release vertical federated kernel binary classification model and vertical federated random forest model. They have been tested to be more efficient than existing vertical federated learning models in our practice. Besides the novel FL algorithm examples, we also release a machine communication module. The uniform data transfer interface supports transferring widely used data formats between machines. We will maintain this platform by adding more functional modules and algorithm examples. The code is available at https://github.com/fedlearnAI/fedlearn-algo.

SCSS-Net: Superpoint Constrained Semi-supervised Segmentation Network for 3D Indoor Scenes

Many existing deep neural networks (DNNs) for 3D point cloud semantic segmentation require a large amount of fully labeled training data. However, manually assigning point-level labels on the complex scenes is time-consuming. While unlabeled point clouds can be easily obtained from sensors or reconstruction, we propose a superpoint constrained semi-supervised segmentation network for 3D point clouds, named as SCSS-Net. Specifically, we use the pseudo labels predicted from unlabeled point clouds for self-training, and the superpoints produced by geometry-based and color-based Region Growing algorithms are combined to modify and delete pseudo labels with low confidence. Additionally, we propose an edge prediction module to constrain the features from edge points of geometry and color. A superpoint feature aggregation module and superpoint feature consistency loss functions are introduced to smooth the point features in each superpoint. Extensive experimental results on two 3D public indoor datasets demonstrate that our method can achieve better performance than some state-of-the-art point cloud segmentation networks and some popular semi-supervised segmentation methods with few labeled scenes.

Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation

Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide an insight into spatial manipulation modules. Firstly, we find that the smaller the rotational degree of freedom (RDF) of objects is, the more easily these objects are handled by these DNNs. Then, we investigate the effect of the popular T-Net module and find that it could not reduce the RDF of objects. Motivated by the above two issues, we propose a rotation transformation network for point cloud analysis, called RTN, which could reduce the RDF of input 3D objects to 0. The RTN could be seamlessly inserted into many existing DNNs for point cloud analysis. Extensive experimental results on 3D point cloud classification and segmentation tasks demonstrate that the proposed RTN could improve the performances of several state-of-the-art methods significantly.