Federated Learning (FL) trains a black-box and high-dimensional model among different clients by exchanging parameters instead of direct data sharing, which mitigates the privacy leak incurred by machine learning. However, FL still suffers from membership inference attacks (MIA) or data reconstruction attacks (DRA). In particular, an attacker can extract the information from local datasets by constructing DRA, which cannot be effectively throttled by existing techniques, e.g., Differential Privacy (DP). In this paper, we aim to ensure a strong privacy guarantee for FL under DRA. We prove that reconstruction errors under DRA are constrained by the information acquired by an attacker, which means that constraining the transmitted information can effectively throttle DRA. To quantify the information leakage incurred by FL, we establish a channel model, which depends on the upper bound of joint mutual information between the local dataset and multiple transmitted parameters. Moreover, the channel model indicates that the transmitted information can be constrained through data space operation, which can improve training efficiency and the model accuracy under constrained information. According to the channel model, we propose algorithms to constrain the information transmitted in a single round of local training. With a limited number of training rounds, the algorithms ensure that the total amount of transmitted information is limited. Furthermore, our channel model can be applied to various privacy-enhancing techniques (such as DP) to enhance privacy guarantees against DRA. Extensive experiments with real-world datasets validate the effectiveness of our methods.
Visually Impaired Assistance (VIA) aims to automatically help visually impaired (VI) handle daily activities. The advancement of VIA primarily depends on developments in Computer Vision (CV) and Natural Language Processing (NLP), both of which exhibit cutting-edge paradigms with large models (LMs). Furthermore, LMs have shown exceptional multimodal abilities to tackle challenging physically-grounded tasks such as embodied robots. To investigate the potential and limitations of state-of-the-art (SOTA) LMs' capabilities in VIA applications, we present an extensive study for the task of VIA with LMs (\textbf{VIALM}). In this task, given an \textit{image} illustrating the physical environments and a \textit{linguistic request} from a VI user, VIALM aims to output step-by-step \textit{guidance} to assist the VI user in fulfilling the request grounded in the environment. The study consists of a survey reviewing recent LM research and benchmark experiments examining selected LMs' capabilities in VIA. The results indicate that while LMs can augment VIA, their output cannot be well \textit{grounded} in reality (i.e., 25.7\% GPT-4's responses) and lacks \textit{fine-grained} guidance (i.e., 32.1\% GPT-4's responses).
Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD), as we expect that MOS can be used to assess how close synthesized speech is to the natural human voice. We propose MOS-FAD, where MOS can be leveraged at two key points in FAD: training data selection and model fusion. In training data selection, we demonstrate that MOS enables effective filtering of samples from unbalanced datasets. In the model fusion, our results demonstrate that incorporating MOS as a gating mechanism in FAD model fusion enhances overall performance.
As attitude and motion sensing components, inertial sensors are widely used in various portable devices. But the severe errors of inertial sensors restrain their function, especially the trajectory recovery and semantic recognition. As a mainstream signal processing method, wavelet is hailed as the mathematical microscope of signal due to the plentiful and diverse wavelet basis functions. However, complicated noise types and application scenarios of inertial sensors make selecting wavelet basis perplexing. To this end, we propose a wavelet dynamic selection network (WDSNet), which intelligently selects the appropriate wavelet basis for variable inertial signals. In addition, existing deep learning architectures excel at extracting features from input data but neglect to learn the characteristics of target categories, which is essential to enhance the category awareness capability, thereby improving the selection of wavelet basis. Therefore, we propose a category representation mechanism (CRM), which enables the network to extract and represent category features without increasing trainable parameters. Furthermore, CRM transforms the common fully connected network into category representations, which provide closer supervision to the feature extractor than the far and trivial one-hot classification labels. We call this process of imposing interpretability on a network and using it to supervise the feature extractor the feature supervision mechanism, and its effectiveness is demonstrated experimentally and theoretically in this paper. The enhanced inertial signal can perform impracticable tasks with regard to the original signal, such as trajectory reconstruction. Both quantitative and visual results show that WDSNet outperforms the existing methods. Remarkably, WDSNet, as a weakly-supervised method, achieves the state-of-the-art performance of all the compared fully-supervised methods.
\textit{Relative overgeneralization} (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior of other agents. In early work, optimism has been shown to mitigate the \textit{RO} problem when using tabular Q-learning. However, with function approximation optimism can amplify overestimation and thus fail on complex tasks. On the other hand, recent deep multi-agent policy gradient (MAPG) methods have succeeded in many complex tasks but may fail with severe \textit{RO}. We propose a general, yet simple, framework to enable optimistic updates in MAPG methods and alleviate the RO problem. Specifically, we employ a \textit{Leaky ReLU} function where a single hyperparameter selects the degree of optimism to reshape the advantages when updating the policy. Intuitively, our method remains optimistic toward individual actions with lower returns which are potentially caused by other agents' sub-optimal behavior during learning. The optimism prevents the individual agents from quickly converging to a local optimum. We also provide a formal analysis from an operator view to understand the proposed advantage transformation. In extensive evaluations on diverse sets of tasks, including illustrative matrix games, complex \textit{Multi-agent MuJoCo} and \textit{Overcooked} benchmarks, the proposed method\footnote{Code can be found at \url{https://github.com/wenshuaizhao/optimappo}.} outperforms strong baselines on 13 out of 19 tested tasks and matches the performance on the rest.
Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations(semantic \& acoustic) and using two sequence-to-sequence tasks to enable training with minimal supervision. However, existing methods suffer from information redundancy and dimension explosion in semantic representation, and high-frequency waveform distortion in discrete acoustic representation. Autoregressive frameworks exhibit typical instability and uncontrollability issues. And non-autoregressive frameworks suffer from prosodic averaging caused by duration prediction models. To address these issues, we propose a minimally-supervised high-fidelity speech synthesis method, where all modules are constructed based on the diffusion models. The non-autoregressive framework enhances controllability, and the duration diffusion model enables diversified prosodic expression. Contrastive Token-Acoustic Pretraining (CTAP) is used as an intermediate semantic representation to solve the problems of information redundancy and dimension explosion in existing semantic coding methods. Mel-spectrogram is used as the acoustic representation. Both semantic and acoustic representations are predicted by continuous variable regression tasks to solve the problem of high-frequency fine-grained waveform distortion. Experimental results show that our proposed method outperforms the baseline method. We provide audio samples on our website.
Artificial Intelligence (AI), a cornerstone of 21st-century technology, has seen remarkable growth in China. In this paper, we examine China's AI development process, demonstrating that it is characterized by rapid learning and differentiation, surpassing the export-oriented growth propelled by Foreign Direct Investment seen in earlier Asian industrializers. Our data indicates that China currently leads the USA in the volume of AI-related research papers. However, when we delve into the quality of these papers based on specific metrics, the USA retains a slight edge. Nevertheless, the pace and scale of China's AI development remain noteworthy. We attribute China's accelerated AI progress to several factors, including global trends favoring open access to algorithms and research papers, contributions from China's broad diaspora and returnees, and relatively lax data protection policies. In the vein of our research, we have developed a novel measure for gauging China's imitation of US research. Our analysis shows that by 2018, the time lag between China and the USA in addressing AI research topics had evaporated. This finding suggests that China has effectively bridged a significant knowledge gap and could potentially be setting out on an independent research trajectory. While this study compares China and the USA exclusively, it's important to note that research collaborations between these two nations have resulted in more highly cited work than those produced by either country independently. This underscores the power of international cooperation in driving scientific progress in AI.
High-content cellular imaging, transcriptomics, and proteomics data provide rich and complementary views on the molecular layers of biology that influence cellular states and function. However, the biological determinants through which changes in multi-omics measurements influence cellular morphology have not yet been systematically explored, and the degree to which cell imaging could potentially enable the prediction of multi-omics directly from cell imaging data is therefore currently unclear. Here, we address the question of whether it is possible to predict bulk multi-omics measurements directly from cell images using Image2Omics -- a deep learning approach that predicts multi-omics in a cell population directly from high-content images stained with multiplexed fluorescent dyes. We perform an experimental evaluation in gene-edited macrophages derived from human induced pluripotent stem cell (hiPSC) under multiple stimulation conditions and demonstrate that Image2Omics achieves significantly better performance in predicting transcriptomics and proteomics measurements directly from cell images than predictors based on the mean observed training set abundance. We observed significant predictability of abundances for 5903 (22.43%; 95% CI: 8.77%, 38.88%) and 5819 (22.11%; 95% CI: 10.40%, 38.08%) transcripts out of 26137 in M1 and M2-stimulated macrophages respectively and for 1933 (38.77%; 95% CI: 36.94%, 39.85%) and 2055 (41.22%; 95% CI: 39.31%, 42.42%) proteins out of 4986 in M1 and M2-stimulated macrophages respectively. Our results show that some transcript and protein abundances are predictable from cell imaging and that cell imaging may potentially, in some settings and depending on the mechanisms of interest and desired performance threshold, even be a scalable and resource-efficient substitute for multi-omics measurements.
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves model learning with planning. Recent methods further utilize policy learning, value estimation, and, self-supervised learning as auxiliary objectives. In this paper we show that, surprisingly, a simple representation learning approach relying only on a latent dynamics model trained by latent temporal consistency is sufficient for high-performance RL. This applies when using pure planning with a dynamics model conditioned on the representation, but, also when utilizing the representation as policy and value function features in model-free RL. In experiments, our approach learns an accurate dynamics model to solve challenging high-dimensional locomotion tasks with online planners while being 4.1 times faster to train compared to ensemble-based methods. With model-free RL without planning, especially on high-dimensional tasks, such as the DeepMind Control Suite Humanoid and Dog tasks, our approach outperforms model-free methods by a large margin and matches model-based methods' sample efficiency while training 2.4 times faster.