Although Vision Language Models (VLMs) have shown generalization in medical imaging, pathology presents unique challenges due to ultra-high resolution, complex tissue structures, and nuanced semantics. These factors make pathology VLMs prone to hallucinations, i.e., generating outputs inconsistent with visual evidence, which undermines clinical trust. Existing RAG approaches in this domain largely depend on text-based knowledge bases, limiting their ability to leverage diagnostic visual cues. To address this, we propose Patho-AgenticRAG, a multimodal RAG framework with a database built on page-level embeddings from authoritative pathology textbooks. Unlike traditional text-only retrieval systems, it supports joint text–image search, enabling retrieval of textbook pages that contain both the queried text and relevant visual cues, thus avoiding the loss of critical image-based information. Patho-AgenticRAG also supports reasoning, task decomposition, and multi-turn search interactions, improving accuracy in complex diagnostic scenarios. Experiments show that Patho-AgenticRAG significantly outperforms existing multimodal models in complex pathology tasks like multiple-choice diagnosis and visual question answering.

Recent advances in vision-language models (VLMs) have enabled broad progress in the general medical field. However, pathology still remains a more challenging sub-domain, with current pathology-specific VLMs exhibiting limitations in both diagnostic accuracy and reasoning plausibility. Such shortcomings are largely attributable to the nature of current pathology datasets, which are primarily composed of image–description pairs that lack the depth and structured diagnostic paradigms employed by real-world pathologists. In this study, we leverage pathology textbooks and real-world pathology experts to construct high-quality, reasoning-oriented datasets. Building on this, we introduce Patho-R1, a multimodal RL-based pathology Reasoner, trained through a three-stage pipeline: (1) continued pretraining on 3.5 million image-text pairs for knowledge infusion; (2) supervised fine-tuning on 500k high-quality Chain-of-Thought samples for reasoning incentivizing; (3) reinforcement learning using Group Relative Policy Optimization and Decoupled Clip and Dynamic sAmpling Policy Optimization strategies for multimodal reasoning quality refinement. To further assess the alignment quality of our dataset, we propose Patho-CLIP, trained on the same figure-caption corpus used for continued pretraining. Comprehensive experimental results demonstrate that both Patho-CLIP and Patho-R1 achieve robust performance across a wide range of pathology-related tasks, including zero-shot classification, cross-modal retrieval, Visual Question Answering, and Multiple Choice Question.

Distributed learning is the standard for training large-scale models across private data silos, offering privacy and efficiency but facing challenges in Byzantine robustness and communication efficiency. Existing Byzantine-robust and communication-efficient methods rely on full gradient information, and they only converge to an unnecessarily large neighborhood around the solution. Motivated by these issues, we propose a novel Byzantine-robust and communication-efficient stochastic distributed learning method that imposes no requirements on batch size and converges to a smaller neighborhood, aligning with the theoretical lower bound. Our key innovation is leveraging Polyak Momentum to mitigate the noise caused by both biased compressors and stochastic gradients, thus defending against Byzantine workers under information compression. We provide proof of tight complexity bounds for nonconvex smooth loss functions. Finally, we validate the practical significance of our algorithm through an extensive series of experiments, benchmarking its performance on both binary classification and image classification tasks.

Federated learning is often used in environments with many unverified participants. Therefore, federated learning under adversarial attacks receives significant attention. This paper proposes an algorithmic framework for list-decodable federated learning, where a central server maintains a list of models, with at least one guaranteed to perform well. The framework has no strict restriction on the fraction of honest clients, extending the applicability of Byzantine federated learning to the scenario with more than half adversaries. Assuming the variance of gradient noise in stochastic gradient descent is bounded, we prove a convergence theorem of our method for strongly convex and smooth losses. Experimental results, including image classification tasks with both convex and non-convex losses, demonstrate that the proposed algorithm can withstand the malicious majority under various attacks.

Due to increasing interest in collaborative and distributed learning, there has been a significant focus on Byzantine robustness. In Byzantine robust distributed learning, a central server aims to train a machine learning model using data that are distributed among multiple workers. However, a small percentage of these workers may deviate from the prescribed algorithm and send malicious messages. To address this type of attacks, resilient training algorithms combine stochastic gradient descent (SGD) with various robust aggregation rules. Previous work has emphasized the importance of reducing gradient noise in SGD to differentiate malicious updates from normal ones, by applying variance reduction techniques to tackle this issue. This paper aims to advance this frontier by using local adaptive momentum as a means to improve the robustness of SGD against Byzantine attacks. In line with this objective, our study introduces Byz-AdaVR-EF21, a method designed to withstand Byzantine behavior that applies adaptive stochastic gradient variance reduction with communication compression. Each worker calculates the local adaptive momentum to simultaneously achieve variance reduction and fast convergence. These features are crucial for more effective countering of Byzantine workers. Additionally, the use of communication compression provides the added benefit of enabling more efficient communication. Extensive experiments have been conducted to showcase the effectiveness of the proposed algorithm.

Byzantine machine learning has garnered considerable attention in light of the unpredictable faults that can occur in large-scale distributed learning systems. The key to secure resilience against Byzantine machines in distributed learning is resilient aggregation mechanisms. Although abundant resilient aggregation rules have been proposed, they are designed in ad-hoc manners, imposing extra barriers on comparing, analyzing, and improving the rules across performance criteria. This paper studies near-optimal aggregation rules using clustering in the presence of outliers. Our outlier-robust clustering approach utilizes geometric properties of the update vectors provided by workers. Our analysis show that constant approximations to the 1-center and 1-mean clustering problems with outliers provide near-optimal resilient aggregators for metric-based criteria, which have been proven to be crucial in the homogeneous and heterogeneous cases respectively. In addition, we discuss two contradicting types of attacks under which no single aggregation rule is guaranteed to improve upon the naive average. Based on the discussion, we propose a two-phase resilient aggregation framework. We run experiments for image classification using a non-convex loss function. The proposed algorithms outperform previously known aggregation rules by a large margin with both homogeneous and heterogeneous data distributions among non-faulty workers. Code and appendix are available at https://github.com/jerry907/AAAI24-RASHB.

Abstract Many graph products have been applied to generate complex networks with striking properties observed in real-world systems. In this paper, we propose a simple generative model for simplicial networks by iteratively using edge corona product. We present a comprehensive analysis of the structural properties of the network model, including degree distribution, diameter, clustering coefficient, as well as distribution of clique sizes, obtaining explicit expressions for these relevant quantities, which agree with the behaviors found in diverse real networks. Moreover, we obtain exact expressions for all the eigenvalues and their associated multiplicities of the normalized Laplacian matrix, based on which we derive explicit formulas for mixing time, mean hitting time and the number of spanning trees. Thus, as previous models generated by other graph products, our model is also an exactly solvable one, whose structural properties can be analytically treated. More interestingly, the expressions for the spectra of our model are also exactly determined, which is sharp contrast to previous models whose spectra can only be given recursively at most. This advantage makes our model a good test bed and an ideal substrate network for studying dynamical processes, especially those closely related to the spectra of normalized Laplacian matrix, in order to uncover the influences of simplicial structure on these processes.

It has been recently established that for second-order consensus dynamics with additive noise, the performance measures, including the vertex coherence and network coherence defined, respectively, as the steady-state variance of the deviation of each vertex state from the average and the average steady-state variance of the system, are closely related to the biharmonic distances. However, direct computation of biharmonic distances is computationally infeasible for huge networks with millions of vertices. In this article, leveraging the implicit fact that both vertex and network coherence can be expressed in terms of the diagonal entries of pseudoinverse$\boldsymbol {{L}}^{2\dagger }$of the square of graph Laplacian, we develop a nearly linear-time algorithm to approximate all diagonal entries of$\boldsymbol {{L}}^{2\dagger }$, which has a theoretically guaranteed error for each diagonal entry. The key ingredient of our approximation algorithm is an integration of the Johnson–Lindenstrauss lemma and Laplacian solvers. Extensive numerical experiments on real-life and model networks are presented, which indicate that our approximation algorithm is both efficient and accurate and is scalable to large-scale networks with millions of vertices.

We study second-order consensus dynamics with random additive disturbances. To quantify the robustness of these networks, we investigate three different performance measures: the steady-state variance of pairwise differences between vertex states, the steady-state variance of the deviation of each vertex state from the average, and the total steady-state variance of the system. We show that these performance measures are closely related to the concept of biharmonic distance; the square of the biharmonic distance plays a similar role in the system performance as resistance distance plays in the performance of first-order noisy consensus dynamics. We then define the new concepts of biharmonic Kirchhoff index and vertex centrality based on the biharmonic distance. We further derive analytical results for the performance measures and concepts for complete graphs, star graphs, cycles, and paths, and we use this analysis to compare the asymptotic behavior of the steady-state variance in first- and second-order systems. Finally, we propose a theoretically guaranteed approximation algorithm to estimate the total steady-state variance, which has a complexity of nearly linear time with respect to the number of edges. Extensive experiments results validate both efficiency and accuracy of our algorithm.

The vast majority of real-world networks are scale-free, loopy, and sparse, with a power-law degree distribution and a constant average degree. In this paper, we study first-order consensus dynamics in binary scale-free networks, where vertices are subject to white noise. We focus on the coherence of networks characterized in terms of the H2-norm, which quantifies how closely the agents track the consensus value. We first provide a lower bound of coherence of a network in terms of its average degree, which is independent of the network order. We then study the coherence of some sparse, scale-free real-world networks, which approaches a constant. We also study numerically the coherence of Barabási-Albert networks and high-dimensional random Apollonian networks, which also converges to a constant when the networks grow. Finally, based on the connection of coherence and the Kirchhoff index, we study analytically the coherence of two deterministically growing sparse networks and obtain the exact expressions, which tend to small constants. Our results indicate that the effect of noise on the consensus dynamics in power-law networks is negligible. We argue that scale-free topology, together with loopy structure, is responsible for the strong robustness with respect to noisy consensus dynamics in power-law networks.

We study the problem of maximizing the number of spanning trees in a connected graph with n vertices and m edges, by adding at most k edges from a given set of q candidate edges, a problem that has applications in many domains. We give both algorithmic and hardness results for this problem: 1) We give a greedy algorithm that obtains an approximation ratio of (1 - 1/e - ∈) in the exponent of the number of spanning trees for any ∈ > 0 in time Õ(m∈-1+ (n + q)∈-3), where Õ(·) hides poly log(n) factors. Our running time is optimal with respect to the input size, up to logarithmic factors, and improves on the O(n3) running time of the previous proposed greedy algorithm with an approximation ratio (1 - 1/e) in the exponent. Notably, the independence of our running time of k is novel, compared to conventional top-k selections on graphs that usually run in Ω(mk) time. 2) We show the exponential inapproximability of this problem by proving that there exists a constant c > 0 such that it is NP-hard to approximate the optimum number of spanning trees in the exponent within (1 - c).

The problem of selecting a group of vertices under certain constraints that maximize their joint centrality arises in many practical scenarios. In this paper, we extend the notion of current flow closeness centrality (CFCC) to a set of vertices in a graph, and investigate the problem of selecting a subset S to maximizes its CFCC C(S), with the cardinality constraint |S| = k. We show the NP-hardness of the problem, but propose two greedy algorithms to minimize the reciprocal of C(S). We prove the approximation ratios by showing the monotonicity and supermodularity. A proposed deterministic greedy algorithm has an approximation factor and cubic running time. To compare with, a proposed randomized algorithm gives -approximation in nearly-linear time, for any ? > 0. Extensive experiments on model and real networks demonstrate the effectiveness and efficiency of the proposed algorithms, with the randomized algorithm being applied to massive networks with more than a million vertices.

Hierarchical product of graphs has found wide applications in various fields, e.g. polymer and biological networks. In this paper, we study the topological and spectral properties of hierarchical graphs as a model of complex networks, which are generated by iterative hierarchical product of complete graphs. We first derive analytically various critical structural properties of the hierarchical graphs, including degree distribution, clustering coefficient, average distance, degree correlations and modularity, and show that they exhibit simultaneously the striking properties of many real networks. We then fully characterize the eigenvalues and eigenvectors of the adjacency matrix and Laplacian matrix pencil of the hierarchical graphs, with the latter subsuming both Laplacian matrix and signless Laplacian matrix. We finally study the susceptible-infectious-susceptible model on the hierarchical graphs and determine the epidemic threshold based on the spectral radius of the adjacency matrix.

The hierarchical graphs and Sierpiński graphs are constructed iteratively, which have the same number of vertices and edges at any iteration, but exhibit quite different structural properties: the hierarchical graphs are nonfractal and small-world, while the Sierpiński graphs are fractal and "large-world." Both graphs have found broad applications. In this paper, we study consensus problems in hierarchical graphs and Sierpiński graphs, focusing on three important quantities of consensus problems, that is, convergence speed, delay robustness, and coherence for first-order (and second-order) dynamics, which are, respectively, determined by algebraic connectivity, maximum eigenvalue, and sum of reciprocal (and square of reciprocal) of each nonzero eigenvalue of Laplacian matrix. For both graphs, based on the explicit recursive relation of eigenvalues at two successive iterations, we evaluate the second smallest eigenvalue, as well as the largest eigenvalue, and obtain the closed-form solutions to the sum of reciprocals (and square of reciprocals) of all nonzero eigenvalues. We also compare our obtained results for consensus problems on both graphs and show that they differ in all quantities concerned, which is due to the marked difference of their topological structures.

The problem of increasing the centrality of a network node arises in many practical applications. In this paper, we study the optimization problem of maximizing the information centrality Iv of a given node v in a network with n nodes and m edges, by creating k new edges incident to v. Since Iv is the reciprocal of the sum of resistance distance Rv between v and all nodes, we alternatively consider the problem of minimizing Rv by adding k new edges linked to v. We show that the objective function is monotone and supermodular. We provide a simple greedy algorithm with an approximation factor (1 − 1/e) and O(n^3) running time. To speed up the computation, we also present an algorithm to compute (1 − 1/e − epsilon) approximate resistance distance Rv after iteratively adding k edges, the running time of which is Otilde(mk*epsilon^−2) for any epsilon > 0, where the Otilde(·) notation suppresses the poly(log n) factors. We experimentally demonstrate the effectiveness and efficiency of our proposed algorithms.

The Kirchhoff index, defined as the sum of effective resistances over pairs all of nodes, is of primary significance in diverse contexts of complex networks. In this paper, we propose to use the rate at which the Kirchhoff index changes with respect to the change of resistance of an edge as a measure of importance for this edge in weighted networks. For an arbitrary edge, we explicitly determine the change of the Kirchhoff index and express it in terms of the biharmonic distance between its end nodes, and thus call this centrality as biharmonic distance related centrality (BDRC). We show that BDRC has a better discriminating power than those commonly used metrics, such as edge betweenness and spanning edge centrality. We give an efficient algorithm that provides an approximation of biharmonic distance for all edges in nearly linear time of the number of edges, with a high probability. Experiment results validate the efficiency and accuracy of the presented algorithm.

In this paper, we study the first-order consensus algorithm in the small-world Farey graph where agents are driven by white noise, aiming to unveil the effect of small-world topology on the robustness of the consensus algorithm. We characterize the coherence of the Farey graph in terms of the |$H_2$|-norm of the system, the square of which equals the steady-state variance and thus captures how closely agents track the consensus value. Based on the particular network structure, we derive an exact expression for the coherence in the Farey graph, whose dominant behavior scales logarithmically with the system size. To uncover the role of small-world topology, we also derive an analytical solution for the coherence of first-order consensus in the regular ring lattice sharing the same average degree as the Farey graph, whose dominant term grows linearly with the system size, implying that the small-world structure strongly affects the performance of the consensus algorithm.