Blog

Swarm-Coder · Network Science × RecSys

Swarm-Coder 搭建日志：从零构建低成本多SLM代码生成集群

2026-04-03 8 min read Project: Swarm-Coder

用 Network Science 思维打造一个「蜂群」架构。Phase 1 完成: LangGraph workflow, popularity bias penalty 路由算法, Gini 系数指标。低成本 vLLM + Ollama 方案。

MLE LangGraph Network Science vLLM
Anatomy of a Recommendation Graph

2026-04-01 10 min read Series: Part 3

Taking MovieLens-1M apart as a network: heavy-tailed degree distributions, Lorenz curves for popularity inequality, how SAR's similarity metrics are really network normalization schemes, and why the Recommenders project needs popularity bias metrics.

Network Science RecSys Power Laws SAR Popularity Bias
Measuring What Matters: Fairness and Popularity Bias in Recommender Systems

2026-04-01 12 min read Series: Part 2

Recommender systems amplify popularity through the same preferential attachment that creates scale-free networks. Exploring 10 fairness and bias metrics — Gini index, calibration error, exposure fairness — with math, implementation, and connections to network science.

Fairness RecSys Network Science Popularity Bias
Why Networks Matter for Recommendations

2026-04-01 12 min read Series: Part 1

Every recommendation system is secretly a network problem. Exploring user-item bipartite graphs, power-law degree distributions, community structure, link prediction, and the spectral theory behind GNN-based recommenders.

Network Science RecSys Graph Theory Spectral Methods