AI 与机器学习2017arxiv.org
用神经网络进行关系推理
Relational Reasoning with Neural Networks
进阶 · 约 60 分钟读完前置知识：深度学习基础、视觉问答（VQA）、关系推理任务
导读
这篇论文（DeepMind 的 Relation Network 模块）研究如何让神经网络完成「关系推理」，也就是把场景中的对象两两配对判断它们之间的关系，再把结果汇总成整体答案。核心做法是把一个简单、可插拔的 Relation Network 模块嵌入现有网络，在 CLEVR 视觉问答和 bAbI 等需要关系推理的任务上显著提升表现。
HN 关注点：DeepMind 再次把「经典 AI 的结构」与深度学习结合的基本研究方向，以及这类模块究竟为何能表示关系、能否泛化到其他领域。
后来怎么样
Relation Network 成为 CLEVR 等关系推理任务上的代表性方法和常用基线，并推动了后续关系网络、交互网络与结构化视觉推理研究。
HN 评论精选
这几条评论里：质疑 2 补充 1 亲历 1
补充DeepMind 的强项在于把经典 AI 技术与深度学习结合，并呼吁加大这类基础研究的投入。
很酷！让我想起最近在 HN 上讨论过的 SHRDLU。几点想法：1）果然是 DeepMind 的论文。我很喜欢他们在神经网络和深度学习上做的这种「基础」研究，看到新论文总是很兴奋。2）希望能有更多对这类基础 ML 研究的投入，这里的「基础」不是指容易，而是指研究不同类问题该怎么处理。DeepMind 很多重大突破似乎都来自把经典 AI/CS 技术与深度学习、优化结合起来：AlphaGo 是把树搜索和深度网络结合，由网络来评估棋局这个难的部分；深度强化学习是把已有的 Q-Learning 等强化学习技术适配到深度网络架构；神经图灵机是把经典计算模型变得可微，让网络「学」排序这类算法；可微神经计算机则是引入可寻址的外部记忆，让网络能做图上的路径查找。我认为未来很多有趣的工作会来自重新审视经典技术。
TFortunato查看英文原文
Very cool! Not quite the same, but brings to mind SHRDLU, which was recently discussed here. The first few thoughts I had on seeing this: 1) Of course this is by DeepMind! Why would I think anything different. (I love the "basic" research they are doing on NNs & Deep Learning, and am always excited to see a new paper by them). 2) I would love to see more investment into this kind of basic ML research. (By that I don't mean "easy", but addressing the fundamentals of how to approach different types / classes of problems). A lot of where the DeepMind guys seem to be finding these big wins is in combining "classic" AI / CS techniques with Deep Learning / Optimization. Examples (And I'm a novice at deep learning, so someone PLEASE PLEASE correct me if I'm wrong): AlphaGo - Take a technique like Tree Search for playing a game, and combine with deep networks for the tricky bit of evaluating play positions Deep Reinforcement Learning - Q-Learning and other reinforcement techniques have been around for a while, but they adapted them to a deep neural net architecture Neural Turing Machines - Took a classical model of computation and made it differentiable, alowing for a neural net to "learn" algorithms like sorting. Deep Neural Computing - Figured out how to add and address external memory in a differentiable computer, allowing a neural net to solve problems like path finding on a graph. Where I think a lot of cool stuff is going to continue to come from is by revisiting classic techniques, and figuring out how they can be adapted to a differentiable / optimizible architecture. Or taking a classic problem and finding an efficient way to evaluate "goodness" of an answer that lends itself to being used in an optimization problem. Again, not saying it is easy, but I wonder how much "low hanging fruit" there is in revisiting classic algorithms and GOFAI techniques, and asking "can I use this in a Neural Net or adapt this to be differentiable so that I can learn or optimize the tricky bits?" I'm sure I'm glossing over a lot / missing the point of a lot of it - like I said, just a noob whose super excited about this stuff :-)
质疑肯定论文的意义，但追问其结论能否推广到差异很大的领域。
我不熟悉关系推理方向的研究，他们测试的这类子问题看起来定义得相当清楚，但即便如此这似乎仍是相当有意义的进展。能否有参与研究的人进一步说明，他们对关系推理能泛化到与测试领域很不相同的其他领域的信心有多大？
3pt14159查看英文原文
I'm not familiar with research on relational reasoning, and the subset they're working with seems pretty well defined, but even so this seems like a pretty meaningful step forward. Can anyone involved in the research comment further on how confident they are that RR is generalizable across dissimilar domains to the one tested?
质疑追问架构与所处理结构之间的对应关系为何成立。
能否更详细地解释，某些神经网络为什么天然能够编码和解读特定结构？为什么 Relation Network 能捕捉关系，而循环神经网络能捕捉序列数据？
empath75查看英文原文
Can someone go in to more detail about how certain neural networks inherently are able to encode and interpret particular structures? Why RNs capture relations and Recurent neural networks can capture sequential data?
亲历感叹研究进展之快，令人有被超越的焦虑。
我的博士论文要没了 :( 他们快得不是一个头脑能追上的。
albertTJames查看英文原文
here goes my phd thesis :( They are too fast for a single mind to beat.
相关资源
从这篇论文所有 HN 讨论帖的全部评论里整理出来的链接。
- 评论区提到的论文
历次讨论
- 2017Hacker News 讨论帖137 分 · 13 评
同领域还值得读
DeepSeek-R1：通过强化学习激励 LLM 的推理能力
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
研究如何用强化学习激励大语言模型的推理能力，提出 DeepSeek-R1，并探讨 RL 训练对模型推理表现的影响。
AI 与机器学习2025 · 1,351 分 · 1,056 评 · 引用 30进阶 · 约 80 分钟编辑精选1-bit LLM 时代：面向低成本计算的三值参数
The Era of 1-bit LLMs: ternary parameters for cost-effective computing
提出用三值参数 {-1, 0, 1} 替代 LLM 中的浮点权重，即所谓“1-bit LLM”。
AI 与机器学习2024 · 1,040 分 · 447 评 · 引用 19进阶 · 约 45 分钟编辑精选DeepSeek-V3.2：推进开放大语言模型的前沿
DeepSeek-v3.2: Pushing the frontier of open large language models
这是 DeepSeek-V3.2 的技术报告，延续了 DeepSeek 开源权重模型的路线，目标是让开放模型继续逼近甚至追平前沿闭源模型。
AI 与机器学习2025 · 982 分 · 465 评进阶 · 约 90 分钟编辑精选通过自我对弈与通用强化学习掌握国际象棋和将棋（AlphaZero）
Mastering Chess and Shogi by Self-Play with General Reinforcement Learning
DeepMind 的 AlphaZero 论文：用通用强化学习算法（自我博弈 + MCTS + 神经网络），从零开始仅数小时训练便在国际象棋和将棋上击败了世界顶级引擎 Stock…
AI 与机器学习2017 · 539 分 · 270 评 · 引用 13进阶 · 约 90 分钟编辑精选用强化学习发现更快的矩阵乘法算法
Discovering faster matrix multiplication algorithms with reinforcement learning
论文提出 AlphaTensor，用强化学习搜索矩阵乘法算法。
AI 与机器学习2022 · 518 分 · 111 评专业 · 约 90 分钟编辑精选