paper-with-me

Papers

Understanding and Tackling Over-Dilution in Graph Neural Networks

2025-08-22 · Junhyun Lee, Veronika Thost, Bumsoo Kim, Jaewoo Kang, Tengfei Ma arxiv

Message Passing Neural Networks (MPNNs) hold a key position in machine learning on graphs, but they struggle with unintended behaviors, such as over-smoothing and over-squashing, due to irregular data structures. The observation and formulation of these limitations have become foundational in constructing more informative graph representations. In this paper, we delve into the limitations of MPNNs, focusing on aspects that have previously been overlooked. Our observations reveal that even within a single layer, the information specific to an individual node can become significantly diluted. To delve into this phenomenon in depth, we present the concept of Over-dilution and formulate it with two dilution factors: intra-node dilution for attribute-level and inter-node dilution for node-level representations. We also introduce a transformer-based solution that alleviates over-dilution and complements existing node embedding methods like MPNNs. Our findings provide new insights and contribute to the development of informative representations. The implementation and supplementary materials are publicly available at https://github.com/LeeJunHyun/NATR.

📄 PDF Abstract BibTeX arXiv:2508.16829

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions

2022-11-04 · Gaurav Verma, Vishwa Vinay, Ryan A. Rossi, Srijan Kumar

As multimodal learning finds applications in a wide variety of high-stakes societal tasks, investigating their robustness becomes important. Existing work has focused on understanding the robustness of vision-and-languag…

SLASH the Sink: Sharpening Structural Attention Inside LLMs

2026-05-11 · Yiming Liu, Bin Lu, Xinbing Wang, Chenghu Zhou 외 arxiv

Large Language Models (LLMs) show remarkable semantic understanding but often struggle with structural understanding when processing graph topologies in a serialized format. Existing solutions rely on training external g…

Relieving the Over-Aggregating Effect in Graph Transformers

2025-10-24 · Junshu Sun, Wanxing Chang, Chenxue Yang, Qingming Huang 외 arxiv

Graph attention has demonstrated superior performance in graph learning tasks. However, learning from global interactions can be challenging due to the large number of nodes. In this paper, we discover a new phenomenon t…

Graph Learning

When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In natural language understanding (NLU) production systems, the end users' evolving needs necessitate the addition of new abilities, indexed by discrete symbols, requiring additional training data and resulting in dynami…

Intent RecognitionNatural Language UnderstandingSemantic Parsing

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

2026-06-05 · Cong Chen, Guo Gan, Kaixiang Ji, ZhaoYang Zhang 외 arxiv

Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to deco…