FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions

• URL: http://arxiv.org/abs/2511.12628v1
• Date: Sun, 16 Nov 2025 14:40:58 GMT
• Title: FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions
• Authors: Ke Hu, Liyao Xiang, Peng Tang, Weidong Qiu,
• Abstract summary: FedTopo is a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE)<n>Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines.
• Score: 35.0734004020033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for high-dimensional visual tasks. We propose FedTopo, a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE) to leverage topological information, yielding coherently aligned cross-client representations by Topological Alignment Loss (TAL). First, Topology-Guided Block Screening (TGBS) automatically selects the most topology-informative block, i.e., the one with maximal topological separability, whose persistence-based signatures best distinguish within- versus between-class pairs, ensuring that subsequent analysis focuses on topology-rich features. Next, this block yields a compact Topological Embedding, which quantifies the topological information for each client. Finally, a Topological Alignment Loss (TAL) guides clients to maintain topological consistency with the global model during optimization, reducing representation drift across rounds. Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines.

Related papers

• TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation [70.23578202012048]
  Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch.<n>We propose TagaVLM (Topology-Aware Global Action reasoning), an end-to-end framework that explicitly injects topological structures into the VLM backbone.<n>To enhance topological node information, an Interleaved Navigation Prompt strengthens node-level visual-text alignment.<n>With the embedded topological graph, the model is capable of global action reasoning, allowing for robust path correction.
  arXiv  Detail & Related papers  (2026-03-03T13:28:07Z)
• Bridging Structure and Appearance: Topological Features for Robust Self-Supervised Segmentation [8.584363058858935]
  Self-supervised semantic segmentation methods often fail when faced with appearance ambiguities.<n>We argue that this is due to an over-reliance on unstable, appearance-based features such as shadows, glare, and local textures.<n>We propose textbfGASeg, a novel framework that bridges appearance and geometry by leveraging stable topological information.
  arXiv  Detail & Related papers  (2025-12-30T05:34:28Z)
• Classification of Firn Data via Topological Features [2.3592914313389253]
  We evaluate the performance of topological features for generalizable and robust classification of firn image data.<n>Firn refers to layers of granular snow within glaciers that haven't been compressed into ice.
  arXiv  Detail & Related papers  (2025-04-22T14:33:33Z)
• Conformable Convolution for Topologically Aware Learning of Complex Anatomical Structures [38.20599800950335]
  We introduce Conformable Convolution, a novel convolutional layer designed to explicitly enforce topological consistency.<n>Topological Posterior Generator (TPG) module identifies key topological features and guides the convolutional layers.<n>We showcase the effectiveness of our framework in the segmentation task, where preserving the interconnectedness of structures is critical.
  arXiv  Detail & Related papers  (2024-12-29T22:41:33Z)
• Topograph: An efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation [78.54656076915565]
  Topological correctness plays a critical role in many image segmentation tasks.<n>Most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy.<n>We propose a novel, graph-based framework for topologically accurate image segmentation.
  arXiv  Detail & Related papers  (2024-11-05T16:20:14Z)
• TopoFR: A Closer Look at Topology Alignment on Face Recognition [58.45515807380505]
  We propose TopoFR, a novel FR model that leverages a topological structure alignment strategy called PTSA and a hard sample mining strategy named SDE.<n> PTSA uses persistent homology to align the topological structures of the input and latent spaces, effectively preserving the structure information and improving the generalization performance of FR model.<n> Experimental results on popular face benchmarks demonstrate the superiority of our TopoFR over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-14T14:58:30Z)
• When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning [19.566775406771757]
  We bridge adversarial graph learning with the emerging tools from computational topology, namely, persistent homology representations of graphs.<n>We introduce the concept of witness complex to adversarial analysis on graphs, which allows us to focus only on the salient shape characteristics of graphs.<n>Our experiments across six datasets demonstrate that Witness Graph Topological Layer boosts the robustness of GNNs across a range of perturbations and against a range of adversarial attacks.
  arXiv  Detail & Related papers  (2024-09-21T14:53:32Z)
• Edge Classification on Graphs: New Directions in Topological Imbalance [53.42066415249078]
  We identify a novel Topological Imbalance Issue', which arises from the skewed distribution of edges across different classes. We introduce Topological Entropy (TE), a novel topological-based metric that measures the topological imbalance for each edge. We develop two strategies - Topological Reweighting and TE Wedge-based Mixup - to focus training on (synthetic) edges based on their TEs.
  arXiv  Detail & Related papers  (2024-06-17T16:02:36Z)
• Understanding Token-level Topological Structures in Transformer-based Time Series Forecasting [52.364260925700485]
  Transformer-based methods have achieved state-of-the-art performance in time series forecasting (TSF)<n>It remains unclear whether existing Transformers fully leverage the intrinsic topological structure among tokens throughout intermediate layers.<n>We propose the Topology Enhancement Method (TEM), a novel Transformer-based TSF method that explicitly and adaptively preserves token-level topology.
  arXiv  Detail & Related papers  (2024-04-16T07:21:39Z)
• Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing [67.83086131278904]
  Topology-imbalance is a graph-specific imbalance problem caused by the uneven topology positions of labeled nodes. We propose a novel position-aware graph structure learning framework named PASTEL. Our key insight is to enhance the connectivity of nodes within the same class for more supervision information.
  arXiv  Detail & Related papers  (2022-08-17T14:04:21Z)
• Topology-Aware Segmentation Using Discrete Morse Theory [38.65353702366932]
  We propose a new approach to train deep image segmentation networks for better topological accuracy. We identify global structures, including 1D skeletons and 2D patches, which are important for topological accuracy. On diverse datasets, our method achieves superior performance on both the DICE score and topological metrics.
  arXiv  Detail & Related papers  (2021-03-18T02:47:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.