How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing

📅 2026-09-04
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
研究通过有效流计数、跨流残差权重和流间余弦相似性分析了DeepSeek-V4-Flash中四流残差路径的使用情况,发现模型主要利用约两个流,且后期混合对性能影响不大。
📝 Abstract
Hyper-Connections and their manifold-constrained variant mHC widen a residual pathway from one stream to n, yet how trained models use this capacity remains unclear: how broadly blocks read and write, how strongly the residual pathway mixes streams, and whether the streams carry distinct representations. We examine these properties in the four-stream residual pathway of DeepSeek-V4-Flash using effective stream counts, cross-stream residual weights, and inter-stream cosine similarity. Read/write routing is concentrated but varies across depth: a typical attention or FFN site effectively uses about two streams, while the dominant stream changes across layers and the representations remain directionally distinct. Residual mixing is modest and occurs primarily in early layers; in layers 22-42, the pathway mostly carries each stream forward separately. Targeted interventions establish the functional significance of these patterns. Replacing the late mixers by identity increases C4 perplexity by only 1.9% and preserves the six-task average score, whereas replacing the early mixers increases perplexity by 41%. Fixing each early mixer to its C4 diagnostic mean increases perplexity by only 0.2% and reduces the average score by 0.25 percentage points, showing that its site-specific structure matters more than its token-wise variation on the evaluated metrics. Likewise, retaining the three largest routing weights per token at every site increases perplexity by at most 2.7% and changes the average score by at most 0.4 points. Thus, the studied model realizes only part of the flexibility afforded by four-stream mHC: individual blocks rarely require all four streams, and late residual mixing provides little measured benefit.
Problem

Research questions and friction points this paper is trying to address.

multi-stream
residual pathway
representation
mixing
routing
Innovation

Methods, ideas, or system contributions that make the work stand out.

mHC
residual mixing
stream routing
effective stream counts
🔎 Similar Papers