English
Related papers

Related papers: Lost in Tokenization: Fundamental Trade-offs in Gr…

200 papers

A foundation model like GPT elicits many emergent abilities, owing to the pre-training with broad inclusion of data and the use of the powerful Transformer architecture. While foundation models in natural languages are prevalent, can we…

Machine Learning · Computer Science 2025-06-18 Ziyuan Tang , Jie Chen

Transformers serve as the backbone architectures of Foundational Models, where domain-specific tokenizers allow them to adapt to various domains. Graph Transformers (GTs) have recently emerged as leading models in geometric deep learning,…

Neural and Evolutionary Computing · Computer Science 2025-04-03 Limei Wang , Kaveh Hassani , Si Zhang , Dongqi Fu , Baichuan Yuan , Weilin Cong , Zhigang Hua , Hao Wu , Ning Yao , Bo Long

Graph Neural Networks (GNNs) are widely used in graph data mining tasks. Traditional GNNs follow a message passing scheme that can effectively utilize local and structural information. However, the phenomena of over-smoothing and…

Machine Learning · Computer Science 2025-04-14 Zijie Zhou , Zhaoqi Lu , Xuekai Wei , Rongqin Chen , Shenghui Zhang , Pak Lon Ip , Leong Hou U

The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. In this work, we introduce a graph…

Machine Learning · Computer Science 2026-03-13 Zeyuan Guo , Enmao Diao , Cheng Yang , Chuan Shi

Transformers have demonstrated success in graph learning, particularly for node-level tasks. However, existing methods encounter an information bottleneck when generating graph-level representations. The prevalent single token paradigm…

Machine Learning · Computer Science 2026-02-11 Ruixiang Wang , Yuyang Hong , Shiming Xiang , Chunhong Pan

Message-passing graph neural networks (GNNs) excel at capturing local relationships but struggle with long-range dependencies in graphs. In contrast, graph transformers (GTs) enable global information exchange but often oversimplify the…

Machine Learning · Computer Science 2024-10-08 Dexiong Chen , Till Hendrik Schulz , Karsten Borgwardt

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Machine Learning · Computer Science 2025-12-01 Wei Shi , Yuan Cao

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions…

Machine Learning · Computer Science 2024-06-05 Hongkang Li , Meng Wang , Tengfei Ma , Sijia Liu , Zaixi Zhang , Pin-Yu Chen

Graph embedding based on random-walks supports effective solutions for many graph-related downstream tasks. However, the abundance of embedding literature has made it increasingly difficult to compare existing methods and to identify…

Machine Learning · Computer Science 2021-10-26 Zexi Huang , Arlei Silva , Ambuj Singh

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Machine Learning · Computer Science 2026-05-14 Amirmehdi Jafari Fesharaki , Mohammadamin Rami , Aslan Tchamkerten

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to…

Graph Transformers are popular neural networks that extend the well-known Transformer architecture to the graph domain. These architectures operate by applying self-attention on graph nodes and incorporating graph structure through the use…

Machine Learning · Computer Science 2025-02-04 Linus Bao , Emily Jin , Michael Bronstein , İsmail İlkan Ceylan , Matthias Lanzinger

While there has been a large body of research attempting to circumvent tokenization for language modeling (Clark et al., 2022; Xue et al., 2022), the current consensus is that it is a necessary initial step for designing state-of-the-art…

Computation and Language · Computer Science 2025-04-11 Nived Rajaraman , Jiantao Jiao , Kannan Ramchandran

We revisit a simple model class for machine learning on graphs, where a random walk on a graph produces a machine-readable record, and this record is processed by a deep neural network to directly make vertex-level or graph-level…

Machine Learning · Computer Science 2025-03-06 Jinwoo Kim , Olga Zaghen , Ayhan Suleymanzade , Youngmin Ryou , Seunghoon Hong

Random walks are widely used for mining networks due to the computational efficiency of computing them. For instance, graph representation learning learns a d-dimensional embedding space, so that the nodes that tend to co-occur on random…

Social and Information Networks · Computer Science 2024-05-24 Sam F. L. Windels , Noel Malod-Dognin , Natasa Przulj

Graphs (networks) are ubiquitous and allow us to model entities (nodes) and the dependencies (edges) between them. Learning a useful feature representation from graph data lies at the heart and success of many machine learning tasks such as…

Node embeddings have become an ubiquitous technique for representing graph data in a low dimensional space. Graph autoencoders, as one of the widely adapted deep models, have been proposed to learn graph embeddings in an unsupervised way by…

Machine Learning · Computer Science 2019-08-13 Vaibhav , Po-Yao Huang , Robert Frederking

Graph embedding maps a graph into a convenient vector-space representation for graph analysis and machine learning applications. Many graph embedding methods hinge on a sampling of context nodes based on random walks. However, random walks…

Machine Learning · Computer Science 2021-10-18 Sadamori Kojaku , Jisung Yoon , Isabel Constantino , Yong-Yeol Ahn

The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification…

Machine Learning · Computer Science 2018-06-11 Sergey Ivanov , Evgeny Burnaev

Graphs are often used to organize data because of their simple topological structure, and therefore play a key role in machine learning. And it turns out that the low-dimensional embedded representation obtained by graph representation…

Machine Learning · Computer Science 2021-01-05 Xing Li , Wei Wei , Xiangnan Feng , Zhiming Zheng
‹ Prev 1 2 3 10 Next ›