On how to avoid exacerbating spurious correlations when models are overparameterized

Overparameterized models fail to generalize well in the presence of data imbalance even when combined with traditional techniques for mitigating imbalances. This paper focuses on imbalanced classification datasets, in which a small subset of the population -- a minority -- may contain features that correlate spuriously with the class label. For a parametric family of cross-entropy loss modifications and a representative Gaussian mixture model, we derive non-asymptotic generalization bounds on the worst-group error that shed light on the role of different hyper-parameters. Specifically, we prove that, when appropriately tuned, the recently proposed VS-loss learns a model that is fair towards minorities even when spurious features are strong. On the other hand, alternative heuristics, such as the weighted CE and the LA-loss, can fail dramatically. Compared to previous works, our bounds hold for more general models, they are non-asymptotic, and, they apply even at scenarios of extreme imbalance.

Analyzing the Adoption Challenges of the Internet of Things (IoT) and Artificial Intelligence (AI) for Smart Cities in China

Smart cities play a vital role in the growth of a nation. In recent years, several countries have made huge investments in developing smart cities to offer sustainable living. However, there are some challenges to overcome in smart city development, such as traffic and transportation man-agement, energy and water distribution and management, air quality and waste management monitoring, etc. The capabilities of the Internet of Things (IoT) and artificial intelligence (AI) can help to achieve some goals of smart cities, and there are proven examples from some cities like Singapore, Copenhagen, etc. However, the adoption of AI and the IoT in developing countries has some challenges. The analysis of challenges hindering the adoption of AI and the IoT are very limited. This study aims to fill this research gap by analyzing the causal relationships among the challenges in smart city development, and contains several parts that conclude the previous scholars work, as well as independent research and investigation, such as data collection and analysis based on DEMATEL. In this paper, we have reviewed the literature to extract key chal-lenges for the adoption of AI and the IoT. These helped us to proceed with the investigation and analyze the adoption status. Therefore, using the PRISMA method, 10 challenges were identified from the literature review. Subsequently, determination of the causal inter-relationships among the key challenges based on expert opinions using DEMATEL is performed. This study explored the driving and dependent power of the challenges, and causal relationships between the barriers were established.

Experimental quantum adversarial learning with programmable superconducting qubits

Quantum computing promises to enhance machine learning and artificial intelligence. Different quantum algorithms have been proposed to improve a wide spectrum of machine learning tasks. Yet, recent theoretical works show that, similar to traditional classifiers based on deep classical neural networks, quantum classifiers would suffer from the vulnerability problem: adding tiny carefully-crafted perturbations to the legitimate original data samples would facilitate incorrect predictions at a notably high confidence level. This will pose serious problems for future quantum machine learning applications in safety and security-critical scenarios. Here, we report the first experimental demonstration of quantum adversarial learning with programmable superconducting qubits. We train quantum classifiers, which are built upon variational quantum circuits consisting of ten transmon qubits featuring average lifetimes of 150 $\mu$s, and average fidelities of simultaneous single- and two-qubit gates above 99.94% and 99.4% respectively, with both real-life images (e.g., medical magnetic resonance imaging scans) and quantum data. We demonstrate that these well-trained classifiers (with testing accuracy up to 99%) can be practically deceived by small adversarial perturbations, whereas an adversarial training process would significantly enhance their robustness to such perturbations. Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.

i-Razor: A Neural Input Razor for Feature Selection and Dimension Search in Large-Scale Recommender Systems

Input features play a crucial role in the predictive performance of DNN-based industrial recommender systems with thousands of categorical and continuous fields from users, items, contexts, and their interactions. Noisy features and inappropriate embedding dimension assignments can impair the performance of recommender systems and introduce unnecessary complexity in model training and online serving. Optimizing the input configuration of DNN models, including feature selection and embedding dimension assignment, has become one of the essential topics in feature engineering. Typically, feature selection and embedding dimension search are optimized sequentially, i.e., feature selection is performed first, followed by embedding dimension search to determine the optimal dimension size for each selected feature. In contrast, this paper studies the joint optimization of feature selection and embedding dimension search. To this end, we propose a differentiable neural \textbf{i}nput \textbf{razor}, namely \textbf{i-Razor}. Specifically, inspired by recent advances in neural architecture search, we introduce an end-to-end differentiable model to learn the relative importance between different embedding regions of each feature. Furthermore, a flexible pruning algorithm is proposed to simultaneously achieve feature filtering and dimension size derivation. Extensive experiments on two large-scale public datasets in the Click-Through-Rate (CTR) prediction task demonstrate the efficacy and superiority of i-Razor in balancing model complexity and performance.

XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding

Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated Conditional Position Encoding module is proposed to deal with the input sequence of variable lengths, and it additionally extracts local layout information from both textual and visual modalities while generating position embeddings. Experiment results show that our XYLayoutLM achieves competitive results on document understanding tasks.

InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training

Denoising diffusion probabilistic models (diffusion models for short) require a large number of iterations in inference to achieve the generation quality that matches or surpasses the state-of-the-art generative models, which invariably results in slow inference speed. Previous approaches aim to optimize the choice of inference schedule over a few iterations to speed up inference. However, this results in reduced generation quality, mainly because the inference process is optimized separately, without jointly optimizing with the training process. In this paper, we propose InferGrad, a diffusion model for vocoder that incorporates inference process into training, to reduce the inference iterations while maintaining high generation quality. More specifically, during training, we generate data from random noise through a reverse process under inference schedules with a few iterations, and impose a loss to minimize the gap between the generated and ground-truth data samples. Then, unlike existing approaches, the training of InferGrad considers the inference process. The advantages of InferGrad are demonstrated through experiments on the LJSpeech dataset showing that InferGrad achieves better voice quality than the baseline WaveGrad under same conditions while maintaining the same voice quality as the baseline but with $3$x speedup ($2$ iterations for InferGrad vs $6$ iterations for WaveGrad).

QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task

Quality Estimation, as a crucial step of quality control for machine translation, has been explored for years. The goal is to investigate automatic methods for estimating the quality of machine translation results without reference translations. In this year's WMT QE shared task, we utilize the large-scale XLM-Roberta pre-trained model and additionally propose several useful features to evaluate the uncertainty of the translations to build our QE system, named \textit{QEMind}. The system has been applied to the sentence-level scoring task of Direct Assessment and the binary score prediction task of Critical Error Detection. In this paper, we present our submissions to the WMT 2021 QE shared task and an extensive set of experimental results have shown us that our multilingual systems outperform the best system in the Direct Assessment QE task of WMT 2020.

Differentially Private Ensemble Classifiers for Data Streams

Learning from continuous data streams via classification/regression is prevalent in many domains. Adapting to evolving data characteristics (concept drift) while protecting data owners' private information is an open challenge. We present a differentially private ensemble solution to this problem with two distinguishing features: it allows an \textit{unbounded} number of ensemble updates to deal with the potentially never-ending data streams under a fixed privacy budget, and it is \textit{model agnostic}, in that it treats any pre-trained differentially private classification/regression model as a black-box. Our method outperforms competitors on real-world and simulated datasets for varying settings of privacy, concept drift, and data distribution.

Subtle Inverse Crimes: Naïvely training machine learning algorithms could lead to overly-optimistic results

While open databases are an important resource in the Deep Learning (DL) era, they are sometimes used "off-label": data published for one task are used for training algorithms for a different one. This work aims to highlight that in some cases, this common practice may lead to biased, overly-optimistic results. We demonstrate this phenomenon for inverse problem solvers and show how their biased performance stems from hidden data preprocessing pipelines. We describe two preprocessing pipelines typical of open-access databases and study their effects on three well-established algorithms developed for Magnetic Resonance Imaging (MRI) reconstruction: Compressed Sensing (CS), Dictionary Learning (DictL), and DL. In this large-scale study we performed extensive computations. Our results demonstrate that the CS, DictL and DL algorithms yield systematically biased results when na\"ively trained on seemingly-appropriate data: the Normalized Root Mean Square Error (NRMSE) improves consistently with the preprocessing extent, showing an artificial increase of 25%-48% in some cases. Since this phenomenon is generally unknown, biased results are sometimes published as state-of-the-art; we refer to that as subtle inverse crimes. This work hence raises a red flag regarding na\"ive off-label usage of Big Data and reveals the vulnerability of modern inverse problem solvers to the resulting bias.