Learning Latent Topology for Graph Matching
Graph matching (GM) has been traditionally modeled as a deterministic optimization problem characterized by an affinity matrix under pre-defined graph topology. Though there have been several attempts on learning more effective node-level affinity/representation for matching, they still heavily rely on the initial graph structure/topology which is typically obtained through heuristic ways (e.g. Delauney or $k$-nearest) and will not be adjusted during the learning process to adapt to problem-specific patterns. We argue that a standalone graph representation learning is insufficient for GM task, whereby a GM solver may favor some latent topology other than pre-defined one. Motivated by this hypothesis, we propose to learn latent graph topology in replacement of the fixed topology as input. To this end, we devise two types of latent graph generation procedures in deterministic and generative fashion, respectively. Particularly, the generative procedure emphasizes the across-graph consistency and thus can be viewed as a \textbf{co-generative} model. Our methods show superior performance over previous state-of-the-arts on several benchmarks, thus strongly supporting our hypothesis.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph GenerationGraph MatchingGraph Representation LearningRepresentation LearningSimilar Papers 제목 키워드 기반
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
In this paper, we introduce LATO, a novel topology-preserving latent representation that enables scalable, flow matching-based synthesis of explicit 3D meshes. LATO represents a mesh as a Vertex Displacement Field (VDF) …
LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow
Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model vertices and connectivity jointly in a join…
From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networks (GNNs) on a given graph topology by dynamically learning it. However, most of LGI methods assume to have a (noisy, incomplete, improvable, ...) i…
Uncertainty-aware Efficient Subgraph Isomorphism using Graph Topology
Subgraph isomorphism or subgraph matching is generally considered as an NP-complete problem, made more complex in practical applications where the edge weights take real values and are subject to measurement noise and po…
Computational EfficiencyDisentangling Interpretable Generative Parameters of Random and Real-World Graphs
While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that …
DisentanglementGraph EmbeddingGraph GenerationGraph Representation Learning