paper-with-me

Papers

Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers

2025-01-18 · Xiaoyu Li, YIngyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Zhen Zhuang

Looped Transformers have shown exceptional neural algorithmic reasoning capability in simulating traditional graph algorithms, but their application to more complex structures like hypergraphs remains underexplored. Hypergraphs generalize graphs by modeling higher-order relationships among multiple entities, enabling richer representations but introducing significant computational challenges. In this work, we extend the Loop Transformer architecture's neural algorithmic reasoning capability to simulate hypergraph algorithms, addressing the gap between neural networks and combinatorial optimization over hypergraphs. Specifically, we propose a novel degradation mechanism for reducing hypergraphs to graph representations, enabling the simulation of graph-based algorithms, such as Dijkstra's shortest path. Furthermore, we introduce a hyperedge-aware encoding scheme to simulate hypergraph-specific algorithms, exemplified by Helly's algorithm. We establish theoretical guarantees for these simulations, demonstrating the feasibility of processing high-dimensional and combinatorial data using Loop Transformers. This work highlights the potential of Transformers as general-purpose algorithmic solvers for structured data.

📄 PDF Abstract BibTeX arXiv:2501.10688

Code (0)

등록된 구현이 없습니다.

Tasks

Combinatorial Optimization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation

2026-02-11 · Ahmadreza Jeddi, Marco Ciccone, Babak Taati arxiv

Looped Transformers have emerged as an efficient and powerful class of models for reasoning in the language domain. Recent studies show that these models achieve strong performance on algorithmic and reasoning tasks, sug…

Step-resolved data attribution for looped transformers

2026-02-10 · Georgios Kaissis, David Mildenberger, Juan Felipe Gomez, Martin J. Menten 외 arxiv

We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for $τ$ recurrent iterations to enable latent reasoning. Existing training-data influence e…

Looped Transformers for Length Generalization

2024-09-24 · Ying Fan, Yilun Du, Kannan Ramchandran, Kangwook Lee

Recent work has shown that Transformers trained from scratch can successfully solve various arithmetic and algorithmic tasks, such as adding numbers and computing parity. While these Transformers generalize well on unsee…

Looped Transformers with Layer Normalization Provably Learn the Power Method

2026-05-30 · Lyumin Wu, Chenyang Zhang, Yuan Cao arxiv

Transformers have achieved remarkable success across a wide range of applications, and a growing body of work suggests that part of their strength comes from their ability to learn and execute algorithmic procedures. How…

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

2026-06-30 · Ying Fan, Anej Svete, Kangwook Lee arxiv

Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replaci…