When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment

• URL: http://arxiv.org/abs/2607.27530v1
• Date: Wed, 29 Jul 2026 23:49:37 GMT
• Title: When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment
• Abstract summary: Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect.<n>We show that architectural channelization, not necessarily semantic routing, can be resolved.
• Score: 0.5721241882795979
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect, such as a class label or molecular property. Multiple heads can separate these aspects, but a change in the query head may alter retrieval even when the wrong text is sent to that head. Such behavior demonstrates architectural channelization, not necessarily semantic routing. We examine the conditions under which this distinction can be resolved. Our controlled version of MV-GTA uses deterministic, verifiable text segments; isolated text encoders; view-specific graph heads; and relevance derived from external labels or RDKit descriptors. Correct routing and per-sample derangements form a causal test of whether retrieval depends on content. On BBBP and BACE, correct routing improves label and property nDCG by 0.305 to 0.685 over deranged training. The expected graph head exceeds the best wrong head by 0.303 to 0.453. Topology does not specialize consistently across the two datasets. In a matched three-seed comparison, one joint model obtains mean topology, label, and property nDCG of 0.720/1.000/0.877; three separately trained Single specialists obtain 0.633/0.976/0.859. Property paraphrase augmentation also improves unseen-template nDCG by 0.140 and 0.147 over a matched-exposure canonical control. Consistency and hard-template extensions, however, reduce canonical retrieval in some settings. The evidence is therefore limited to explicit, externally grounded label and property routing and observed multi-interface consolidation. It does not establish free-form routing, consistent three-view specialization, statistical equivalence to specialists, or superior downstream prediction.

Related papers

• Instance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CT [1.3890393030771435]
  We propose Instance-Guided Report Anchoring (IGRA), a model-agnostic module that preserves the correspondence between each annotated abnormality instance and the report finding that describes it.<n>IGRA improves Dice by 22.5% over the strongest image-only baseline (30.93 vs. 25.25) and is comparable to VoxTell on the single-finding subset (30.29 vs. 30.43)
  arXiv  Detail & Related papers  (2026-08-31T22:38:11Z)
• SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification [71.9783246097687]
  SEER hides candidate relations during pair localization, constructs a query-specific view with explicit subject/object roles, and retains the full image and sparse box geometry as complementary evidence.<n>For relation-choice protocols with exact inverse support, an optional refinement swaps the entity roles and changes the forward decision only when exactly one visual state obeys the corresponding inverse relation.<n>The unchanged protocol yields +4.35 to +11.79 on all 2,434 filtered EmbSpatial pair-relation questions across three models.
  arXiv  Detail & Related papers  (2026-08-04T13:16:15Z)
• Toward Semantically-Seeded, Graph-Propagated Impact Analysis Across Software Artifacts: A Vision [0.0]
  We argue for a training-free and interpretable analyzer that fuses both signals over the same embeddings.<n>A small but complete proof-of-concept on a payment subsystem labelled change scenarios shows the mechanism we care about.
  arXiv  Detail & Related papers  (2026-06-17T09:34:56Z)
• SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers [11.601609455691644]
  tool is a mapping-first diagnostic resource for sid tokenizer artifacts.<n>tool reports inspectable artifact profiles before downstream leaderboard scores.
  arXiv  Detail & Related papers  (2026-06-09T03:36:31Z)
• Architecture-Aware Explanation Auditing for Industrial Visual Inspection [1.3054033103300278]
  This paper operationalizes an architecture-aware explanation audit protocol grounded in the native-readout hypothesis.<n>On WM-811K wafer maps (9 classes, 172k images) under a three-seed zero-fill perturbation protocol, ViT-Tiny + Attention Rollout attains Deletion AUC 0.211 against 0.432-0.525 for Swin-Tiny.
  arXiv  Detail & Related papers  (2026-05-14T01:48:00Z)
• From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection [89.52759572485276]
  ARC is a few-shot generalist GAD method that leverages in-context learning and requires only a few labeled normal samples at inference time.<n> ARC and ARC_zero effectively detect anomalies, exhibit strong generalization ability, and perform efficiently under few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2026-02-21T10:59:00Z)
• AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation [36.2420491060406]
  Recent GraphRAG methods integrate graph structures into text indexing and retrieval.<n>We propose a more precise and reliable architecture for knowledge representation and indexing.<n>In our approach, knowledge is stored as knowledge atoms, rather than coarse-grained text chunks.
  arXiv  Detail & Related papers  (2026-02-10T05:57:47Z)
• SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding [56.079013202051094]
  We present SegVG, a novel method transfers the box-level annotation as signals to provide an additional pixel-level supervision for Visual Grounding. This approach allows us to iteratively exploit the annotation as signals for both box-level regression and pixel-level segmentation.
  arXiv  Detail & Related papers  (2024-07-03T15:30:45Z)
• Relation Rectification in Diffusion Model [64.84686527988809]
  We introduce a novel task termed Relation Rectification, aiming to refine the model to accurately represent a given relationship it initially fails to generate. We propose an innovative solution utilizing a Heterogeneous Graph Convolutional Network (HGCN) The lightweight HGCN adjusts the text embeddings generated by the text encoder, ensuring the accurate reflection of the textual relation in the embedding space.
  arXiv  Detail & Related papers  (2024-03-29T15:54:36Z)
• Exploring the Hierarchy in Relation Labels for Scene Graph Generation [75.88758055269948]
  The proposed method can improve several state-of-the-art baselines by a large margin (up to $33%$ relative gain) in terms of Recall@50. Experiments show that the proposed simple yet effective method can improve several state-of-the-art baselines by a large margin.
  arXiv  Detail & Related papers  (2020-09-12T17:36:53Z)
• Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol [87.76993857713217]
  We show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be formulated as a Graph Embedding. Specifically, we analyse the loss functions of three existing state-of-the-art Supervised Domain Adaptation methods and demonstrate that they perform Graph Embedding.
  arXiv  Detail & Related papers  (2020-04-23T15:46:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.