arXiv Machine Learning
Jun 25
Communicability-Inspired Positional Encoding (CIPE)
arXiv:2606. 25293v1 Announce Type: new Abstract: Positional encodings (PEs) are essential for Transformers.
Communicability-Inspired Positional Encoding (CIPE)
Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging.
Related stories
arXiv AI
Jun 26
Rotary Position Encodings for Graphs
arXiv:2509. 22259v4 Announce Type: replace-cross Abstract: We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data.
arXiv AI
Jun 17
Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity
arXiv:2606. 17830v1 Announce Type: cross Abstract: Neural network parameter spaces are inherently non-injective, as distinct parameter configurations can realize identical functions through functional equivalence.
arXiv Machine Learning
22h ago
HyPE-GT: where Graph Transformers meet Hyperbolic Positional Encodings
arXiv:2312. 06576v2 Announce Type: replace Abstract: Graph Transformers (GTs) facilitate the comprehension of complex relationships on graph-structured data by leveraging self-attention of the possible pairs of nodes.
arXiv AI
Jul 28
A Survey of Graph Transformers: Architectures, Theories and Applications
arXiv:2502. 16533v3 Announce Type: replace-cross Abstract: Graph Transformers (GTs) have demonstrated a strong capability in modeling graph structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as over-smoothing and over-squashing.
arXiv Machine Learning
Jul 14
From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers
arXiv:2607. 10677v1 Announce Type: new Abstract: Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood.
arXiv AI
Jul 3
X-LogSMask: Expand Transformer for Graph-Structured Data
arXiv:2607. 01553v1 Announce Type: cross Abstract: Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sparse, structured and multi-scale.
Hugging Face Trending Papers
Jul 20
L1 Augmented Attention as an Improved Vector Similarity Metric
Scaled dot product attention conflates directional alignment and vector magnitude, limiting its effectiveness as a similarity metric in Transformer models. We introduce L1 augmented attention, a simple and computationally parallelizable modification that subtracts a learned, head specific L1 distance between queries and keys from the dot product score.
arXiv Machine Learning
Jun 18
Complementary Attention Head Pruning for Efficient Transformers
arXiv:2606. 19150v1 Announce Type: new Abstract: The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments.
arXiv AI
Jun 4
A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks
arXiv:2510. 24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties across models with different modalities.
arXiv AI
Jul 28
Plain Transformers are Surprisingly Powerful Link Predictors
arXiv:2602. 01553v3 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies.
arXiv AI
Jul 22
Enhancing Transformer-based Routing by Encoding Distance via Relative Positional Encoding
arXiv:2607. 18909v1 Announce Type: new Abstract: This paper explores Relative Positional Encoding (RPE) as an additive bias in Transformer architectures to solve the Team Orienteering Problem.