Mycelium-Index: A Streaming Approximate Nearest Neighbor Index with Myelial Edge Decay, Traffic-Driven Reinforcement, and Adaptive Living Hierarchy

• URL: http://arxiv.org/abs/2604.11274v1
• Date: Mon, 13 Apr 2026 10:30:08 GMT
• Title: Mycelium-Index: A Streaming Approximate Nearest Neighbor Index with Myelial Edge Decay, Traffic-Driven Reinforcement, and Adaptive Living Hierarchy
• Abstract summary: We present mycelium-index, a streaming approximate nearest neighbor (ANN) index for high-dimensional vector spaces.<n>System adapts its topology through myelial edge decay and reinforcement, a traffic-driven living hierarchy, and hybrid deletion.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present mycelium-index, a streaming approximate nearest neighbor (ANN) index for high-dimensional vector spaces, inspired by the adaptive growth patterns of biological mycelium. The system continuously adapts its topology through myelial edge decay and reinforcement, a traffic-driven living hierarchy, and hybrid deletion combining O(1) bypass for cold nodes with O(k) beam-search repair for hub nodes. Experimental evaluation on SIFT-1M demonstrates that mycelium achieves 0.927 +/- 0.028 recall@5 under FreshDiskANN's 100%-turnover benchmark protocol -- within the measurement confidence interval of FreshDiskANN's ~0.95 -- while using 5.7x less RAM (88 MB vs. >500 MB) and achieving 4.7x higher QPS (2,795 vs. ~600). On the static index, at ef=192, mycelium matches HNSW M=16 recall (0.962 vs. 0.965) at 5.2x less RAM (163 MB vs. 854 MB). Performance optimizations including NEON SIMD distance computation, Vec-backed node storage, and bitset visited tracking yield a cumulative 2.7x QPS improvement. A systematic study of ten streaming repair mechanisms finds that geometric heuristics universally fail in high dimensions, while topological mechanisms succeed -- a principle we term the topological repair invariance of high-dimensional ANN graphs.

Related papers

• CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection [0.0]
  CLEAR-MoE is a post-training pipeline that converts a frozen pretrained Vision Transformer (ViT) into a sparse Mixture-of-Experts (MoE) model without updating backbone weights.<n>On a GTX 960, routing and scatter-gather overhead make the CLEAR-MoE FFN 1.3-1.7x slower than the dense routers.
  arXiv  Detail & Related papers  (2026-06-26T18:12:03Z)
• Resource-Efficient Iterative LLM-Based NAS with Feedback Memory [49.44875022114861]
  Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources.<n>We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures.
  arXiv  Detail & Related papers  (2026-03-12T16:00:22Z)
• ECHO: Encoding Communities via High-order Operators [8.970269049715933]
  Community detection in attributed networks faces a fundamental divide: topological algorithms ignore semantic features, while Graph Neural Networks (GNNs) encounter devastating computational bottlenecks.<n>We introduce ECHO, a scalable, self supervised architecture that reframes community detection as an adaptive, multi scale diffusion process.<n>ECHO completely bypasses traditional O(N2) memory bottlenecks without sacrificing the mathematical precision of global gradients.
  arXiv  Detail & Related papers  (2026-02-25T22:14:29Z)
• Reranker Optimization via Geodesic Distances on k-NN Manifolds [0.0]
  We propose Maniscope, a geometric reranking method that computes geodesic distances on k-nearest neighbor (k-NN) equations.<n>Maniscope outperforms HNSW graph-based baseline on the three hardest datasets.<n>Compared to cross-encoder rerankers, Maniscope achieves within 2% accuracy at 10-45x lower latency.
  arXiv  Detail & Related papers  (2026-01-26T07:55:08Z)
• Warp-Cortex: An Asynchronous, Memory-Efficient Architecture for Million-Agent Cognitive Scaling on Consumer Hardware [0.0]
  We present Warp Cortex, an asynchronous architecture that theoretically enables million-agent cognitive scaling.<n>We empirically demonstrate 100 concurrent agents at 2.2 GB total VRAM, with theoretical capacity exceeding 1,000 agents before compute latency becomes the bottleneck.<n>We further introduce Referential Injection, a non-intrusive KV-cache update mechanism that allows asynchronous sub-agents to influence primary generation without stream disruption.
  arXiv  Detail & Related papers  (2026-01-03T23:11:21Z)
• Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies [53.38648279089736]
  Geminet is a lightweight and scalable ML-based TE framework that can handle changing topologies.<n>Its neural network size is only 0.04% to 7% of existing schemes.<n>When trained on large-scale topologies, Geminet consumes under 10 GiB of memory, more than eight times less than the 80-plus GiB required by HARP.
  arXiv  Detail & Related papers  (2025-06-30T09:09:50Z)
• A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization [83.12938977698988]
  Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. Current approaches inadequately address the intrinsic optimization of the co-occurrence matrix $barA$ based on cosine similarity. We propose a Non-Negative Generalized Category Discovery (NN-GCD) framework to address these deficiencies.
  arXiv  Detail & Related papers  (2024-10-29T07:24:11Z)
• A Topological Perspective on Demystifying GNN-Based Link Prediction Performance [72.06314265776683]
  Topological Concentration (TC) is based on the intersection of the local subgraph of each node with the ones of its neighbors. We show that TC has a higher correlation with LP performance than other node-level topological metrics like degree and subgraph density. We propose Approximated Topological Concentration (ATC) and theoretically/empirically justify its efficacy in approximating TC and reducing the complexity.
  arXiv  Detail & Related papers  (2023-10-06T22:07:49Z)
• Dink-Net: Neural Clustering on Large Graphs [59.10189693120368]
  A deep graph clustering method (Dink-Net) is proposed with the idea of dilation and shrink. By discriminating nodes, whether being corrupted by augmentations, representations are learned in a self-supervised manner. The clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss. Compared to the runner-up, Dink-Net 9.62% achieves NMI improvement on the ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges.
  arXiv  Detail & Related papers  (2023-05-28T15:33:24Z)
• Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining [61.09807522366773]
  We introduce an algorithm that approximates the softmax with provable bounds and that dynamically maintains the tree. In our study on datasets with over twenty million targets, our approach cuts error by half in relation to oracle brute-force negative mining.
  arXiv  Detail & Related papers  (2023-03-27T15:18:32Z)
• Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation [25.62587471067468]
  RepUX-Net is a pure CNN architecture with a simple large kernel block design. Inspired by the spatial frequency in the human visual system, we extend to vary the kernel convergence into element-wise setting.
  arXiv  Detail & Related papers  (2023-03-10T08:38:34Z)
• Efficient Cluster-Based k-Nearest-Neighbor Machine Translation [65.69742565855395]
  k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT)
  arXiv  Detail & Related papers  (2022-04-13T05:46:31Z)
• Res-GCNN: A Lightweight Residual Graph Convolutional Neural Networks for Human Trajectory Forecasting [0.0]
  We propose a Residual Graph Convolutional Neural Network (Res-GCNN), which models the interactive behaviors of pedes-trians. Results show an improvement over the state of art by 13.3% on the Final Displacement Error (FDE) which reaches 0.65 meter. The code will be made publicly available on GitHub.
  arXiv  Detail & Related papers  (2020-11-18T11:18:16Z)

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.