REVIEW 6 cited by
Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
read the original abstract
We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between message passing in GNNs and the self-attention mechanism in Transformers. Attention Graphs aggregate attention matrices across Transformer layers and heads to describe how information flows among input nodes. Through experiments on homophilous and heterophilous node classification tasks, we analyze Attention Graphs from a network science perspective and find that: (1) When Graph Transformers are allowed to learn the optimal graph structure using all-to-all attention among input nodes, the Attention Graphs learned by the model do not tend to correlate with the input/original graph structure; and (2) For heterophilous graphs, different Graph Transformer variants can achieve similar performance while utilising distinct information flow patterns. Open source code: https://github.com/batu-el/understanding-inductive-biases-of-gnns
Forward citations
Cited by 6 Pith papers
-
Task complexity shapes internal representations and robustness in neural networks
Harder classification tasks produce neural representations whose accuracy collapses under binarization and shuffling while easier tasks remain robust, defining task complexity via the performance gap between full-prec...
-
SLASH the Sink: Sharpening Structural Attention Inside LLMs
LLMs spontaneously build graph topology inside their attention layers but attention sinks suppress it; SLASH redistributes attention to restore structural understanding without training.
-
SLASH the Sink: Sharpening Structural Attention Inside LLMs
SLASH is a plug-and-play attention redistribution technique that counters attention sinks to enhance LLMs' intrinsic graph topology reconstruction without any training or fine-tuning.
-
When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents
LLM agents exhibit emergent covert numerical coordination in canonical game settings under restricted or absent communication, shaping strategic outcomes.
-
Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning
Spectral features of attention are claimed to classify proof validity with near-perfect effect sizes, but the main evaluation relabels proofs using the classifier's own outputs.
-
SLASH the Sink: Sharpening Structural Attention Inside LLMs
SLASH redistributes attention in LLMs to amplify their spontaneous internal reconstruction of graph topologies, yielding gains on graph and molecular tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.