We thank all reviewers for their constructive comments and address the raised issues below. As described in Secion 3.2 of the manuscript, we introduce the The source code, as mentioned on L141, will be made available to the public. R1: Why the adaptive flow filtering is a better way of reducing artifacts? Our method could be seen as a learnable median filter in spirit. Although the quantitative improvement from the adaptive flow filtering (ada.) is small, this component is important in generating results with higher visual quality SepConv has originally been trained on high-quality videos with large motion.

This paper proposes Constrained Sampling Cluster Model Predictive Path Integral (CSC-MPPI), a novel constrained formulation of MPPI designed to enhance trajectory optimization while enforcing strict constraints on system states and control inputs. Traditional MPPI, which relies on a probabilistic sampling process, often struggles with constraint satisfaction and generates suboptimal trajectories due to the weighted averaging of sampled trajectories. To address these limitations, the proposed framework integrates a primal-dual gradient-based approach and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to steer sampled input trajectories into feasible regions while mitigating risks associated with weighted averaging. First, to ensure that sampled trajectories remain within the feasible region, the primal-dual gradient method is applied to iteratively shift sampled inputs while enforcing state and control constraints. Then, DBSCAN groups the sampled trajectories, enabling the selection of representative control inputs within each cluster. Finally, among the representative control inputs, the one with the lowest cost is chosen as the optimal action. As a result, CSC-MPPI guarantees constraint satisfaction, improves trajectory selection, and enhances robustness in complex environments. Simulation and real-world experiments demonstrate that CSC-MPPI outperforms traditional MPPI in obstacle avoidance, achieving improved reliability and efficiency. The experimental videos are available at https://cscmppi.github.io

This paper presents FedPID, our submission to the Federated Tumor Segmentation Challenge 2024 (FETS24). Inspired by Fed-CostWAvg and FedPIDAvg, our winning contributions to FETS21 and FETS2022, we propose an improved aggregation strategy for federated and collaborative learning. FedCostWAvg is a method that averages results by considering both the number of training samples in each group and how much the cost function decreased in the last round of training. This is similar to how the derivative part of a PID controller works. In FedPIDAvg, we also included the integral part that was missing. Another challenge we faced were vastly differing dataset sizes at each center. We solved this by assuming the sizes follow a Poisson distribution and adjusting the training iterations for each center accordingly. Essentially, this part of the method controls that outliers that require too much training time are less frequently used. Based on these contributions we now adapted FedPIDAvg by changing how the integral part is computed.

Multiplicative noise widely exists in radar images, medical images and other important fields' images. Compared to normal noises, multiplicative noise has a generally stronger effect on the visual expression of images. Aiming at the denoising problem of multiplicative noise, we linearize the nonlocal means algorithm with deep learning and propose a linear attention mechanism based deep nonlocal means filtering (LDNLM). Starting from the traditional nonlocal means filtering, we employ deep channel convolution neural networks to extract the information of the neighborhood matrix and obtain representation vectors of every pixel. Then we replace the similarity calculation and weighted averaging processes with the inner operations of the attention mechanism. To reduce the computational overhead, through the formula of similarity calculation and weighted averaging, we derive a nonlocal filter with linear complexity. Experiments on both simulated and real multiplicative noise demonstrate that the LDNLM is more competitive compared with the state-of-the-art methods. Additionally, we prove that the LDNLM possesses interpretability close to traditional NLM.

Federated learning provides a promising privacy-preserving way for utilizing large-scale private edge data from massive Internet-of-Things (IoT) devices. While existing research extensively studied optimizing the learning process, computing efficiency, and communication overhead, one important and often overlooked aspect is that participants contribute predictive knowledge from their data, impacting the quality of the federated models learned. While FedAvg treats each client equally and assigns weight solely based on the number of samples, the diversity of samples on each client could greatly affect the local update performance and the final aggregated model. In this paper, we propose a novel approach to address this issue by introducing a Weighted Averaging (WeiAvg) framework that emphasizes updates from high-diversity clients and diminishes the influence of those from low-diversity clients. Specifically, we introduced a projection-based approximation method to estimate the diversity of client data, instead of the computation of an entropy. We use the approximation because the locally computed entropy may not be transmitted due to excess privacy risk. Extensive experimental results show that WeiAvg converges faster and achieves higher accuracy than the original FedAvg algorithm and FedProx.

The F1 score (aka F-measure) is a popular metric for evaluating the performance of a classification model. In the case of multi-class classification, we adopt averaging methods for F1 score calculation, resulting in a set of different average scores (macro, weighted, micro) in the classification report. This article looks at the meaning of these averages, how to calculate them, and which one to choose for reporting. Note: Skip this section if you are already familiar with the concepts of precision, recall, and F1 score. Layman definition: Of all the positive predictions I made, how many of them are truly positive?

We showcase a novel solution to a recommendation system problem where we face a perpetual soft item cold start issue. Our system aims to recommend demanded products to prospective sellers for listing in Amazon stores. These products always have only few interactions thereby giving rise to a perpetual soft item cold start situation. Modern collaborative filtering methods solve cold start using content attributes and exploit the existing implicit signals from warm start items. This approach fails in our use-case since our entire item set faces cold start issue always. Our Product Graph has over 500 Million nodes and over 5 Billion edges which makes training and inference using modern graph algorithms very compute intensive. To overcome these challenges we propose a system which reduces the dataset size and employs an improved modelling technique to reduce storage and compute without loss in performance. Particularly, we reduce our graph size using a filtering technique and then exploit this reduced product graph using Weighted Averaging of Messages over Layers (WAML) algorithm. WAML simplifies training on large graphs and improves over previous methods by reducing compute time to 1/7 of LightGCN and 1/26 of Graph Attention Network (GAT) and increasing recall$@100$ by 66% over LightGCN and 2.3x over GAT.

The area of graph embeddings is currently dominated by contrastive learning methods, which demand formulation of an explicit objective function and sampling of positive and negative examples. This creates a conceptual and computational overhead. Simple, classic unsupervised approaches like Multidimensional Scaling (MSD) or the Laplacian eigenmap skip the necessity of tedious objective optimization, directly exploiting data geometry. Unfortunately, their reliance on very costly operations such as matrix eigendecomposition make them unable to scale to large graphs that are common in today's digital world. In this paper we present Cleora: an algorithm which gets the best of two worlds, being both unsupervised and highly scalable. We show that high quality embeddings can be produced without the popular step-wise learning framework with example sampling. An intuitive learning objective of our algorithm is that a node should be similar to its neighbors, without explicitly pushing disconnected nodes apart. The objective is achieved by iterative weighted averaging of node neigbors' embeddings, followed by normalization across dimensions. Thanks to the averaging operation the algorithm makes rapid strides across the embedding space and usually reaches optimal embeddings in just a few iterations. Cleora runs faster than other state-of-the-art CPU algorithms and produces embeddings of competitive quality as measured on downstream tasks: link prediction and node classification. We show that Cleora learns a data abstraction that is similar to contrastive methods, yet at much lower computational cost. We open-source Cleora under the MIT license allowing commercial use under https://github.com/Synerise/cleora.

Improved collaboration techniques for tasks executed collectively by multiple agents can lead to increased amount of information available to the agents, increased efficiency of resource utilization, reduced interference among the agents, and faster task completion. An example of a multiagent task that benefits from collaboration is Collective Transport with Obstacle Avoidance: the task of multiple agents jointly moving an object while navigating around obstacles. We propose a new approach to sharing and aggregation of information among the transporting agents that entails (1) considering all available information instead of only their own most pressing concerns through establishing objectively valued system needs and (2) being persuadable instead of stubborn, through assessing how these needs compare to the needs established by their peers. Our system extends and improves upon the work in (Ferrante et al. 2013), leading to better informed agents making efficient decisions that cause less inter-agent interference and lead to faster and more reliable completion of the collective task.