The rapid development of Internet technology has made social networks central platforms for information dissemination and acquisition. As key participants, users exhibit increasingly complex connection patterns, reflecting the dynamic nature of online interactions. Therefore, in order to better understand and manage social networks, analyzing these connection patterns, particularly identifying the potential connections between users with similar tendencies, has become a critical research focus in social network studies. Nevertheless, the existing methods exhibit limitations in comprehensively harnessing the heterogeneous nature of social networks and usually over-rely on local network structures while neglecting global patterns. To address these problems, we propose an innovative method based on weighted random walks within heterogeneous information networks (HINs). We first employ HINs to structurally represent and systematically organize complex social network data, leveraging meta-paths to model user connection patterns at semantic levels. Then, based on the meta-paths, we develop an adaptive weighted random walk strategy to integrate global structural features with local semantic information and connect users with similar tendencies. Experimental results on both Twitter and public HIN datasets demonstrate that our method outperforms other classical methods in accurately connecting users with similar tendencies.

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central goal of the alignment problem is to adjust the distribution learned by diffusion models such that the generated samples maximize the target reward function. We propose a novel alignment approach, named Direct Noise Optimization (DNO), that optimizes the injected noise during the sampling process of diffusion models. By design, DNO operates at inference-time, and thus is tuning-free and prompt-agnostic, with the alignment occurring in an online fashion during generation. We rigorously study the theoretical properties of DNO and also propose variants to deal with non-differentiable reward functions. Furthermore, we identify that naive implementation of DNO occasionally suffers from the out-of-distribution reward hacking problem, where optimized samples have high rewards but are no longer in the support of the pretrained distribution. To remedy this issue, we leverage classical high-dimensional statistics theory to an effective probability regularization technique. We conduct extensive experiments on several important reward functions and demonstrate that the proposed DNO approach can achieve state-of-the-art reward scores within a reasonable time budget for generation.

Human joints enable precise bending for fine manipulation and complex movements. Similarly, robotic flexibility relies on bending structures, where accurate bending perception is crucial for precise control and enhanced humanrobot interaction. This paper proposes a C-shaped fiber optic array, embedding a fiber Bragg Grating sensor array into a 2 mm thick silicone layer, successfully achieving a highly sensitive (300 pm/N) and electromagnetic interference-resistant bending sensor. The flexible sensor can sensitively detect external stimuli, such as the touch of a 1g weight or a feather, and exhibits a good linear relationship with curvature, facilitating accurate curvature classification. Additionally, leveraging the wearable nature of the sensor, we achieved the detection of finger bending angles. Finally, by attaching the sensor to the wrist and combining it with deep learning algorithms, we achieved 100% gesture recognition accuracy. This sensor holds significant potential for applications in fields such as fruit size classification, rehabilitation healthcare, and human-robot interaction.

Wireless network optimization is essential for improving the network performance in mobile communications. However, due to the stochastic nature of wireless networks, existing schemes based on analytical models and deterministic optimization are less reliable. To this end, we design a framework for robust network optimization based on deep generative models and stochastic optimization. Inspired by the powerful diffusion process, we propose a deep generative simulator to capture the statistical distribution of the network performance. By sampling from the deep generative simulator, we can alleviate the inherent uncertainty related to the network performance and devise an innovative expectation-quantile-based stochastic objective function. The inner expectation is designed for the temporal statistics, while the outer quantile is developed for the spatial statistics. This designated two-tier objective function is capable of mitigating temporal fluctuations and ensuring satisfactory network performance across most geographical grids, thereby achieving robustness. To solve this stochastic optimization problem, a smooth zeroth-order approach is introduced by taking advantage of the unique structure of quantile functions. Through theoretical performance analysis and simulation experiments with real-world datasets, we demonstrate the superiority of our approach over other baseline schemes, highlighting its practical utility in robust network optimization.

Federated Learning (FL) is a promising privacy-preserving distributed learning paradigm but suffers from high communi- cation cost when training large-scale machine learning models. Sign-based methods, such as SignSGD, have been proposed as a biased gradient compression technique for reducing the communication cost. However, sign-based algorithms could diverge under heterogeneous data, which thus motivated the de- velopment of advanced techniques, such as the error-feedback method and stochastic sign-based compression, to fix this issue. Nevertheless, these methods still suffer from slower convergence rates, and none of them allows multiple local SGD updates like FedAvg. In this paper, we propose a novel noisy perturbation scheme with a general symmetric noise distribution for sign-based compression, which not only al- lows one to flexibly control the bias-variance tradeoff for the compressed gradient, but also provides a unified viewpoint to existing stochastic sign-based methods. More importantly, the proposed scheme enables the development of the very first sign-based FedAvg algorithm (z-SignFedAvg) to accelerate the convergence. Theoretically, we show that z-SignFedAvg achieves a faster convergence rate than existing sign-based methods and, under the uniformly distributed noise, can enjoy the same convergence rate as its uncompressed counterpart. Extensive experiments are conducted to demonstrate that the z-SignFedAvg can achieve competitive empirical performance on real datasets and outperforms existing schemes.

In Federated Learning (FL), a framework to train machine learning models across distributed data, well-known algorithms like FedAvg tend to have slow convergence rates, resulting in high communication costs during training. To address this challenge, we introduce FedLion, an adaptive federated optimization algorithm that seamlessly incorporates key elements from the recently proposed centralized adaptive algorithm, Lion [1], into the FL framework. Through comprehensive evaluations on two widely adopted FL benchmarks, we demonstrate that FedLion outperforms previous state-of-the-art adaptive algorithms, including FAFED [2] and FedDA [3]. Moreover, thanks to the use of signed gradients in local training, FedLion substantially reduces data transmission requirements during uplink communication when compared to existing adaptive algorithms, further reducing communication costs. Last but not least, this work also includes a novel theoretical analysis, showcasing that FedLion attains faster convergence rate than established FL algorithms like FedAvg.

In this study, we delve into an emerging optimization challenge involving a black-box objective function that can only be gauged via a ranking oracle—a situation frequently encountered in real-world scenarios, especially when the function is evaluated by human judges. A prominent instance of such a situation is Reinforcement Learning with Human Feedback (RLHF), an approach recently employed to enhance the performance of Large Language Models (LLMs) using human guidance [Ouyang et al. 2022, Liu et al. 2023, OpenAI et al. 2022, Bai et al. 2022]. We introduce ZO-RankSGD, an innovative zeroth-order optimization algorithm designed to tackle this optimization problem, accompanied by theoretical assurances. Our algorithm utilizes a novel rank-based random estimator to determine the descent direction and guarantees convergence to a stationary point. Moreover, ZO-RankSGD is readily applicable to policy optimization problems in Reinforcement Learning (RL), particularly when only ranking oracles for the episode reward are available. Last but not least, we demonstrate the effectiveness of ZO-RankSGD in a novel application: improving the quality of images generated by a diffusion generative model with human ranking feedback. Throughout experiments, we found that ZO-RankSGD can significantly enhance the detail of generated images with only a few rounds of human feedback. Overall, our work advances the field of zeroth-order optimization by addressing the problem of optimizing functions with only ranking feedback, and offers a new and effective approach for aligning Artificial Intelligence (AI) with human intentions.

Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent autoregressive nature of their sampling process. In this work, we propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Specifically, we reformulate the sampling process as solving a system of triangular nonlinear equations through fixed-point iteration. With this innovative formulation, we explore several systematic techniques to further reduce the iteration steps required by the solving process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm that can leverage extra computational and memory resources to increase the sampling speed. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4$\sim$14 times. Notably, when applying ParaTAA with 100 steps DDIM for Stable Diffusion, a widely-used text-to-image diffusion model, it can produce the same images as the sequential sampling in only 7 inference steps. The code is available at https://github.com/TZW1998/ParaTAA-Diffusion.

Subsurface density (SD) is a crucial dynamic environment parameter reflecting a 3-D ocean process and stratification, with significant implications for the physical, chemical, and biological processes of the ocean environment. Thus, accurate SD retrieval is essential for studying dynamic processes in the ocean interior. However, complete spatiotemporally accurate SD retrieval remains a challenge in terms of the equation of state and physical methods. This study proposes a novel multiscale mixed residual transformer (MMRT) neural network method to compensate for the inadequacy of the existing methods in dealing with spatiotemporal nonlinear processes and dependence. Considering the spatial correlation and temporal dependence of dynamic processes within the ocean, the MMRT addresses temporal dependence by fully using the transformer’s processing of time-series data and spatial correlation by compensating for deficiencies in spatial feature information through multiscale mixed residuals. The MMRT model was compared with the existing random forest (RF) and recurrent neural network (RNN) methods. The MMRT model achieves the best accuracy with an average determination coefficient (${R}^{2}$) of 0.988 and an average root mean square error (RMSE) of 0.050 kg/m3 for all layers. The MMRT model not only outperforms the RF and RNN methods regarding reliability and generalization ability when estimating global ocean SD from remote sensing data but also has a more interpretable encoding process. The MMRT model offers a new method for directly estimating SD using multisource satellite observations, providing significant technical support for future remote sensing super-resolution and prediction of subsurface parameters.

We study a matrix recovery problem with unknown correspondence: given the observation matrix $M_o=[A,\tilde P B]$, where $\tilde P$ is an unknown permutation matrix, we aim to recover the underlying matrix $M=[A,B]$. Such problem commonly arises in many applications where heterogeneous data are utilized and the correspondence among them are unknown, e.g., due to data mishandling or privacy concern. We show that, in some applications, it is possible to recover $M$ via solving a nuclear norm minimization problem. Moreover, under a proper low-rank condition on $M$, we derive a non-asymptotic error bound for the recovery of $M$. We propose an algorithm, $\text{M}^3\text{O}$ (Matrix recovery via Min-Max Optimization) which recasts this combinatorial problem as a continuous minimax optimization problem and solves it by proximal gradient with a Max-Oracle. $\text{M}^3\text{O}$ can also be applied to a more general scenario where we have missing entries in $M_o$ and multiple groups of data with distinct unknown correspondence. Experiments on simulated data, the MovieLens 100K dataset and Yale B database show that $\text{M}^3\text{O}$ achieves state-of-the-art performance over several baselines and can recover the ground-truth correspondence with high accuracy.

A complex network is a fundamental tool to describe real-world complex systems, with most real-world systems containing multiple object types and relationships that can be described as heterogeneous information networks. However, with the increasing network complexity, understanding the complex patterns and finding the meta paths or meta-structures of the heterogeneous information networks has become challenging. This paper proposes a sparse representation for heterogeneous information networks and extracts the heterogeneous information atoms that describe the basic connection pattern of the original heterogeneous information network. The heterogeneous information atoms help extract the main meta-paths or meta-structures and understand the complex patterns of the original heterogeneous information network. Furthermore, the heterogeneous information networks can be decomposed, dimension-reduced, and reconstructed through the heterogeneous information atoms. Extensive experimental results demonstrate that heterogeneous information atoms and sparse coding represent the basic connection pattern of real-world heterogeneous information networks. Indeed, the developed method can reconstruct a network with a recovery exceeding 90%.

Interconnect congestion estimation plays an important role in design automation of VLSI designs. This paper presents a novel probabilistic approach to predict the wiring space in two-dimensional arrays. We propose a hierarchical estimation method to derive approximated upper bounds for the wiring space, and we use the net density distribution to predict the routing congestion. Experimental results demonstrate the promising performance of the approach.