无需共享数据，用任务向量拼出661种生物声学分类器
Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data
- 用任务向量算术组合独立训练的编码器，实现多物种分类
- 任务向量近正交，平均法最优，符号冲突使准确率降1-6个百分点
- 适合保护生物多样性监测，支持跨区域零样本迁移
生物声学训练数据分散于不同物种、区域和机构，集中化常不可行。我们发现，通过任务向量算术可将独立微调的BEATs编码器组合成一个包含661个物种的统一分类器，且无需共享原始数据。生物声学任务向量呈近正交（余弦值0.01-0.09），其分离度与频谱分布距离高度一致，符合声学生态位假说。该几何结构使简单平均最优，而符号冲突方法使准确率下降1至6个百分点。组合还产生不对称效应：物种丰富类群准确率相对下降，而稀有类群准确率提升，有利于公平的生物多样性监测。我们验证了所有分类对间线性模式连通性，展示了对新区域的零样本迁移能力，并识别出域否定为组合失效的边界条件。这些结果推动了一种新型协作范式：机构仅共享任务向量即可构建多物种分类器，保障数据隐私。
原文摘要 · Abstract (English)
Training data for bioacoustics is scattered across taxa, regions, and institutions. Centralizing it all is often infeasible. We show that independently fine-tuned BEATs encoders can be composed into a unified 661-species classifier via task vector arithmetic without sharing data. We find that bioacoustic task vectors are near-orthogonal (cosine 0.01-0.09). Their separation aligns closely with spectral distribution distance, a gradient consistent with the acoustic niche hypothesis. This geometry makes simple averaging optimal while sign-conflict methods reduce accuracy by one to six percentage points. Composition also creates an asymmetric gap: species-rich groups lose accuracy relative to joint training while underrepresented taxa gain, a redistribution useful for equitable biodiversity monitoring. We verify linear mode connectivity across all taxonomic pairs, demonstrate zero-shot transfer to new regions, and identify domain negation as a boundary condition where composition fails. These results enable a collaborative paradigm for bioacoustics where institutions share only task vectors to assemble multi-taxa classifiers, preserving data privacy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。