Comprehensive Privacy Analysis on Federated Recommender System against Attribute Inference Attacks

In recent years, recommender systems are crucially important for the delivery of personalized services that satisfy users' preferences. With personalized recommendation services, users can enjoy a variety of recommendations such as movies, books, ads, restaurants, and more. Despite the great benefits, personalized recommendations typically require the collection of personal data for user modelling and analysis, which can make users susceptible to attribute inference attacks. Specifically, the vulnerability of existing centralized recommenders under attribute inference attacks leaves malicious attackers a backdoor to infer users' private attributes, as the systems remember information of their training data (i.e., interaction data and side information). An emerging practice is to implement recommender systems in the federated setting, which enables all user devices to collaboratively learn a shared global recommender while keeping all the training data on device. However, the privacy issues in federated recommender systems have been rarely explored. In this paper, we first design a novel attribute inference attacker to perform a comprehensive privacy analysis of the state-of-the-art federated recommender models. The experimental results show that the vulnerability of each model component against attribute inference attack is varied, highlighting the need for new defense approaches. Therefore, we propose a novel adaptive privacy-preserving approach to protect users' sensitive data in the presence of attribute inference attacks and meanwhile maximize the recommendation accuracy. Extensive experimental results on two real-world datasets validate the superior performance of our model on both recommendation effectiveness and resistance to inference attacks.

EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL

Reinforcement learning (RL) in long horizon and sparse reward tasks is notoriously difficult and requires a lot of training steps. A standard solution to speed up the process is to leverage additional reward signals, shaping it to better guide the learning process. In the context of language-conditioned RL, the abstraction and generalisation properties of the language input provide opportunities for more efficient ways of shaping the reward. In this paper, we leverage this idea and propose an automated reward shaping method where the agent extracts auxiliary objectives from the general language goal. These auxiliary objectives use a question generation (QG) and question answering (QA) system: they consist of questions leading the agent to try to reconstruct partial information about the global goal using its own trajectory. When it succeeds, it receives an intrinsic reward proportional to its confidence in its answer. This incentivizes the agent to generate trajectories which unambiguously explain various aspects of the general language goal. Our experimental study shows that this approach, which does not require engineer intervention to design the auxiliary objectives, improves sample efficiency by effectively directing exploration.

Classical surrogates for quantum learning models

The advent of noisy intermediate-scale quantum computers has put the search for possible applications to the forefront of quantum information science. One area where hopes for an advantage through near-term quantum computers are high is quantum machine learning, where variational quantum learning models based on parametrized quantum circuits are discussed. In this work, we introduce the concept of a classical surrogate, a classical model which can be efficiently obtained from a trained quantum learning model and reproduces its input-output relations. As inference can be performed classically, the existence of a classical surrogate greatly enhances the applicability of a quantum learning strategy. However, the classical surrogate also challenges possible advantages of quantum schemes. As it is possible to directly optimize the ansatz of the classical surrogate, they create a natural benchmark the quantum model has to outperform. We show that large classes of well-analyzed re-uploading models have a classical surrogate. We conducted numerical experiments and found that these quantum models show no advantage in performance or trainability in the problems we analyze. This leaves only generalization capability as possible point of quantum advantage and emphasizes the dire need for a better understanding of inductive biases of quantum learning models.

Self-Supervised Training with Autoencoders for Visual Anomaly Detection

Deep convolutional autoencoders provide an effective tool for learning non-linear dimensionality reduction in an unsupervised way. Recently, they have been used for the task of anomaly detection in the visual domain. By optimising for the reconstruction error using anomaly-free examples, the common belief is that a trained network will have difficulties to reconstruct anomalous parts during the test phase. This is usually done by controlling the capacity of the network by either reducing the size of the bottleneck layer or enforcing sparsity constraints on its activations. However, neither of these techniques does explicitly penalise reconstruction of anomalous signals often resulting in a poor detection. We tackle this problem by adapting a self-supervised learning regime which allows to use discriminative information during training while regularising the model to focus on the data manifold by means of a modified reconstruction error resulting in an accurate detection. Unlike related approaches, the inference of the proposed method during training and prediction is very efficient processing the whole input image in one single step. Our experiments on the MVTec Anomaly Detection dataset demonstrate high recognition and localisation performance of the proposed method. On the texture-subset, in particular, our approach consistently outperforms a bunch of recent anomaly detection methods by a big margin.

Intelligent Reflecting Surface Enabled Multi-Target Sensing

Besides improving communication performance, intelligent reflecting surfaces (IRSs) are also promising enablers for achieving larger sensing coverage and enhanced sensing quality. Nevertheless, in the absence of a direct path between the base station (BS) and the targets, multi-target sensing is generally very difficult, since IRSs are incapable of proactively transmitting sensing beams or analyzing target information. Moreover, the echoes of different targets reflected via the IRS-established virtual links share the same directionality at the BS. In this paper, we study a wireless system comprising a multi-antenna BS and an IRS for multi-target sensing, where the beamforming vector and the IRS phase shifts are jointly optimized to improve the sensing performance. To meet the different sensing requirements, such as a minimum received power and a minimum sensing frequency, we propose three novel IRS-assisted sensing schemes: Time division (TD) sensing, signature sequence (SS) sensing, and hybrid TD-SS sensing. First, for TD sensing, the sensing tasks are performed in sequence over time. Subsequently, a novel signature sequence (SS) sensing scheme is proposed to improve sensing efficiency by establishing a relationship between directions and SSs. To strike a flexible balance between the beam pattern gain and sensing efficiency, we also propose a general hybrid TD-SS sensing scheme with target grouping, where targets belonging to the same group are sensed simultaneously via SS sensing, while the targets in different groups are assigned to orthogonal time slots. By controlling the number of groups, the hybrid TD-SS sensing scheme can provide a more flexible balance between beam pattern gain and sensing frequency. Moreover, ...

User Engagement in Mobile Health Applications

Mobile health apps are revolutionizing the healthcare ecosystem by improving communication, efficiency, and quality of service. In low- and middle-income countries, they also play a unique role as a source of information about health outcomes and behaviors of patients and healthcare workers, while providing a suitable channel to deliver both personalized and collective policy interventions. We propose a framework to study user engagement with mobile health, focusing on healthcare workers and digital health apps designed to support them in resource-poor settings. The behavioral logs produced by these apps can be transformed into daily time series characterizing each user's activity. We use probabilistic and survival analysis to build multiple personalized measures of meaningful engagement, which could serve to tailor content and digital interventions suiting each health worker's specific needs. Special attention is given to the problem of detecting churn, understood as a marker of complete disengagement. We discuss the application of our methods to the Indian and Ethiopian users of the Safe Delivery App, a capacity-building tool for skilled birth attendants. This work represents an important step towards a full characterization of user engagement in mobile health applications, which can significantly enhance the abilities of health workers and, ultimately, save lives.

Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning

In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift. We propose a different approach named virtual homogeneity learning (VHL) to directly "rectify" the data heterogeneity. In particular, VHL conducts FL with a virtual homogeneous dataset crafted to satisfy two conditions: containing no private information and being separable. The virtual dataset can be generated from pure noise shared across clients, aiming to calibrate the features from the heterogeneous clients. Theoretically, we prove that VHL can achieve provable generalization performance on the natural distribution. Empirically, we demonstrate that VHL endows FL with drastically improved convergence speed and generalization performance. VHL is the first attempt towards using a virtual dataset to address data heterogeneity, offering new and effective means to FL.

Multi scale Feature Extraction and Fusion for Online Knowledge Distillation

Online knowledge distillation conducts knowledge transfer among all student models to alleviate the reliance on pre-trained models. However, existing online methods rely heavily on the prediction distributions and neglect the further exploration of the representational knowledge. In this paper, we propose a novel Multi-scale Feature Extraction and Fusion method (MFEF) for online knowledge distillation, which comprises three key components: Multi-scale Feature Extraction, Dual-attention and Feature Fusion, towards generating more informative feature maps for distillation. The multiscale feature extraction exploiting divide-and-concatenate in channel dimension is proposed to improve the multi-scale representation ability of feature maps. To obtain more accurate information, we design a dual-attention to strengthen the important channel and spatial regions adaptively. Moreover, we aggregate and fuse the former processed feature maps via feature fusion to assist the training of student models. Extensive experiments on CIF AR-10, CIF AR-100, and CINIC-10 show that MFEF transfers more beneficial representational knowledge for distillation and outperforms alternative methods among various network architectures

Audio-Visual Wake Word Spotting System For MISP Challenge 2021

This paper presents the details of our system designed for the Task 1 of Multimodal Information Based Speech Processing (MISP) Challenge 2021. The purpose of Task 1 is to leverage both audio and video information to improve the environmental robustness of far-field wake word spotting. In the proposed system, firstly, we take advantage of speech enhancement algorithms such as beamforming and weighted prediction error (WPE) to address the multi-microphone conversational audio. Secondly, several data augmentation techniques are applied to simulate a more realistic far-field scenario. For the video information, the provided region of interest (ROI) is used to obtain visual representation. Then the multi-layer CNN is proposed to learn audio and visual representations, and these representations are fed into our two-branch attention-based network which can be employed for fusion, such as transformer and conformed. The focal loss is used to fine-tune the model and improve the performance significantly. Finally, multiple trained models are integrated by casting vote to achieve our final 0.091 score.

Implicit adaptation of mesh model of transient heat conduction problem

Considering high-temperature heating, the equations of transient heat conduction model require an adaptation, i.e. the dependence of thermophysical parameters of the model on the temperature is to be identified for each specific material to be heated. This problem is most often solved by approximation of the tabular data on the measurements of the required parameters, which can be found in the literature, by means of regression equations. But, for example, considering the steel heating process, this approach is difficult to be implemented due to the lack of tabular discrete measurements for many grades of steel, such as alloyed ones. In this paper, the new approach is proposed, which is based on a solution of a related variational problem. Its main idea is to substitute the adaptation process in the classical sense (i.e., to find the dependencies of thermophysical parameters on temperature) with 'supervised learning' of a mesh model on the basis of the technological data received from the plant. The equations to adjust the parameters of the transient heat conduction model, which are related to the thermophysical coefficients, have been derived. A numerical experiment is conducted for steel of a particular group of grades, for which enough both technological as well as tabular data are available. As a result, the 'trained' mesh model, which has not received explicitly any information about the physical and chemical properties of the heated substance, demonstrated an average error of 18.820 C, which is quite close to the average error of the model adapted classically on the basis of the tabular data (18.10 C).