{"version":"1.0","generated_at":"2026-10-22T12:00:13.447082","id":3542,"slug":"nvidia-kumo-relational-outperforms-supervised-machine-learning-on-relational-data-no-training-required","title":"NVIDIA Kumo Relational 在关系型数据上超越监督式机器学习，且无需训练","summary":"NVIDIA 推出预训练关系型基础模型 Kumo Relational，可直接连接企业数据库，在单次前向传播中完成流失、需求、欺诈等预测，无需任务专用训练、特征工程或表展平。在 15 个数据库的 41 项任务上，它超越监督式关系深度模型与专家工程化 GBDT 流水线；在 SAP SALT 企业基准上，其平均倒数排名（MRR）比 AutoGluon 集成高 8%，并可扩展至 500B+ 行规模。","abstract":"NVIDIA Kumo Relational 在关系型数据上超越监督式机器学习，且无需训练 NVIDIA 推出预训练关系型基础模型 Kumo Relational，可直接连接企业数据库，在单次前向传播中完成流失、需求、欺诈等预测，无需任务专用训练、特征工程或表展平。在 15 个数据库的 41 项任务上，它超越监督式关系深度模型与专家工程化 GBDT 流水线；在 SAP SALT 企业基准上，其平均倒数排名（MRR）比 AutoGluon 集成高 8%，并可扩展至 500B+ 行规模。 NVIDIA 推出预训练关系型基础模型 Kumo Relational，可直接连接企业数据库，在单次前向传播中完成流失、需求、欺诈等预测，无需任务专用训练、特征工程或表展平。在 15 个数据库的 41 项任务上，它超越监督式关系深度模型与专家工程化 GBDT 流水线；在 SAP SALT 企业基准上，其平均倒数排名（MRR）比 AutoGluon 集成高 8%，并可扩展至 500B+ 行规模。 原贴提到：NVIDIA Kumo Relational is a pre-trained relational foundation model that 来源：huggingface.co NVIDIA Kumo Relational 是一个预训练的关系型基础模型，可直接在企业数据库上进行预测。给定一个预测查询，它会收集最多 10,000 个历史样本作为上下文，并在单次前向传播中预测流失、需求或欺诈等结果。它不需要任务专用训练，不需要特征工程，也不需要将表展平。Kumo Relational 是首个在常…","access_level":"member","access_label":"免费阅读","access_mode":"full","is_preview":false,"canonical_url":"https://opc.beizhux.com/content/3542/nvidia-kumo-relational-outperforms-supervised-machine-learning-on-relational-data-no-training-required","html_url":"https://opc.beizhux.com/content/3542/nvidia-kumo-relational-outperforms-supervised-machine-learning-on-relational-data-no-training-required","json_url":"https://opc.beizhux.com/content/3542/nvidia-kumo-relational-outperforms-supervised-machine-learning-on-relational-data-no-training-required.json","published_at":"2026-10-22T02:26:30","updated_at":"2026-10-22T11:33:29","category":{"slug":"ai-business","name":"AI小生意项目库"},"source":{"site":"huggingface.co","author":"Hugging Face Blog","url":"https://huggingface.co/blog/nvidia/kumo-relational"},"tags":["Kumo Relational","NVIDIA","Predictive Query Language","XGBoost","XGBoost替代","上下文学习","企业AI","企业数据库","关系型基础模型","少样本学习","智能体","结构化数据"],"topics":[{"slug":"ai-side-business","name":"AI副业","url":"https://opc.beizhux.com/topics/ai-side-business","reason":"这篇内容命中「项目、小生意、变现」等主题信号。"},{"slug":"ai-tools","name":"AI工具","url":"https://opc.beizhux.com/topics/ai-tools","reason":"这篇内容命中「模型」等主题信号。"},{"slug":"agent-workflow","name":"Agent工作流","url":"https://opc.beizhux.com/topics/agent-workflow","reason":"这篇内容命中「智能体」等主题信号。"}],"keywords":["AI小生意项目库","AI副业","AI工具","Agent工作流","工具","自动化","模型","Cursor","Claude","Agent","智能体","工作流"],"questions":[{"question":"NVIDIA Kumo Relational 在关系型数据上超越监督式机器学习，且无需训练主要讲什么？","answer":"NVIDIA 推出预训练关系型基础模型 Kumo Relational，可直接连接企业数据库，在单次前向传播中完成流失、需求、欺诈等预测，无需任务专用训练、特征工程或表展平。在 15 个数据库的 41 项任务上，它超越监督式关系深度模型与专家工程化 GBDT 流水线；在 SAP SALT 企业基准上，其平均倒数排名（MRR）比 AutoGluon 集成高…"},{"question":"这篇文章最值得关注的要点是什么？","answer":"NVIDIA 推出预训练关系型基础模型 Kumo Relational，可直接连接企业数据库，在单次前向传播中完成流失、需求、欺诈等预测，无需任务专用训练、特征工程或表展平。在 15 个数据库的 41 项任务上，它超越监督式关系深度模型与…；原贴提到：NVIDIA Kumo Relational is a pre-trained relational foundation model that；来源：huggingface.co"},{"question":"这篇文章和哪些AI专题相关？","answer":"它适合放在AI副业、AI工具、Agent工作流专题里阅读。 关联原因：这篇内容命中「项目、小生意、变现」等主题信号。；这篇内容命中「模型」等主题信号。；这篇内容命中「智能体」等主题信号。"},{"question":"阅读这篇文章建议先理解哪些关键词？","answer":"建议先理解AI工具、工具、自动化、模型、Cursor这些关键词，再结合正文判断工具、机会或风险是否值得进入自己的工作流。"}],"terms":[{"slug":"ai-tools-term","name":"AI工具","definition":"在AI觉醒星球里，「AI工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/ai-tools-term","path":"/glossary/ai-tools-term","json_url":"https://opc.beizhux.com/glossary/ai-tools-term.json"},{"slug":"tools","name":"工具","definition":"在AI觉醒星球里，「工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/tools","path":"/glossary/tools","json_url":"https://opc.beizhux.com/glossary/tools.json"},{"slug":"automation","name":"自动化","definition":"在AI觉醒星球里，「自动化」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/automation","path":"/glossary/automation","json_url":"https://opc.beizhux.com/glossary/automation.json"},{"slug":"ai-model","name":"模型","definition":"在AI觉醒星球里，「模型」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/ai-model","path":"/glossary/ai-model","json_url":"https://opc.beizhux.com/glossary/ai-model.json"},{"slug":"cursor","name":"Cursor","definition":"在AI觉醒星球里，「Cursor」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/cursor","path":"/glossary/cursor","json_url":"https://opc.beizhux.com/glossary/cursor.json"},{"slug":"claude","name":"Claude","definition":"在AI觉醒星球里，「Claude」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/claude","path":"/glossary/claude","json_url":"https://opc.beizhux.com/glossary/claude.json"},{"slug":"agent","name":"Agent","definition":"在AI觉醒星球里，「Agent」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/agent","path":"/glossary/agent","json_url":"https://opc.beizhux.com/glossary/agent.json"},{"slug":"ai-agent","name":"智能体","definition":"在AI觉醒星球里，「智能体」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/ai-agent","path":"/glossary/ai-agent","json_url":"https://opc.beizhux.com/glossary/ai-agent.json"}],"preview_hidden_sections":[],"related_items":[{"id":3539,"title":"卡兹克详解 AI 挖出的 PHP2Shell 漏洞：发现只花2天，修复用了两个月","url":"https://opc.beizhux.com/content/3539/ai-php2shell-2","summary":"卡兹克复盘 PHP2Shell 两个高危远程代码执行漏洞的完整处置链路：提前泄密、演示视频流出、多国政府网站预防性下线，到21日晚10点补丁上线；并指出漏洞由 GPT-5.6 Sol 辅助发现，OpenAI 还发布了检测 skill。","access_level":"member"},{"id":3540,"title":"通过一致的标准实现广泛可及","url":"https://opc.beizhux.com/content/3540/broad-access-through-consistent-standards","summary":"OpenAI 说明其如何与分发合作伙伴协作，以维持一致的防护措施、支持负责任的访问，并在使用政策中明确各方预期。","access_level":"member"},{"id":3541,"title":"OpenAI 的 GPT-5.6 Sol 与 Google 的 Gemini 4 Argon 发现影响数百万网站的关键 PHP 漏洞","url":"https://opc.beizhux.com/content/3541/openai-s-gpt-5-6-sol-and-google-s-gemini-4-argon-found-critical-php-flaw-affecting-millions-of-websites","summary":"OpenAI 与 Google 的大模型在 Patch-the-Planet 行动中独立发现了一个影响数百万网站的关键 PHP 漏洞，并与 Wiz、Cloudflare、PHP 开发者及美国 CISA、白宫完成两个月的协同修复。Wiz 指出，大模型能自动适配不同 PHP 版本与内存布局，把过去难以规模化的利用变成可复…","access_level":"member"}],"usage_policy":{"summarizable":true,"preferred_url":"https://opc.beizhux.com/content/3542/nvidia-kumo-relational-outperforms-supervised-machine-learning-on-relational-data-no-training-required","private_fields_excluded":true}}