Papers with Code 아카이브

Graph Regression

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 22
보존된 평가 기록: 239

The regression task is similar to graph classification but using different loss function and performance metric.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/danielegrattarola/spektral

공식 코드

Graph Neural Networks in TensorFlow and Keras with Spektral

https://github.com/diningphil/e-cgmm

공식 코드

Modeling Edge Features with Deep Bayesian Graph Networks

https://github.com/dptech-corp/Uni-Mol

공식 코드

Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+

https://github.com/ejwww/tangnn

공식 코드

TANGNN: a Concise, Scalable and Effective Graph Neural Networks with Top-m Attention Mechanism for Graph Representation Learning

https://github.com/foisunt/hyperaggregation

공식 코드

HyperAggregation: Aggregating over Graph Edges with Hypernetworks

https://github.com/fuvty/DeSCo

공식 코드

DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting

https://github.com/gasmichel/pathnns_expressive

공식 코드

Path Neural Networks: Expressive and Accurate Graph Neural Networks

https://github.com/gbouritsas/graph-substructure-networks

공식 코드

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

https://github.com/georgemlp/canonicalization

공식 코드

A Canonicalization Perspective on Invariant and Equivariant Learning

https://github.com/georgemlp/laplacian-canonization

공식 코드

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

https://github.com/geriskenderi/graph-jepa

공식 코드

Graph-level Representation Learning with Joint-Embedding Predictive Architectures

https://github.com/giannisnik/pi-GNN

공식 코드

Permute Me Softly: Learning Soft Permutations for Graph Representations

https://github.com/gmum/progrest

공식 코드

ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction

https://github.com/goose315/graph_pooling_benchmark

공식 코드

A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizability

https://github.com/graphdeeplearning/benchmarking-gnns

공식 코드

Benchmarking Graph Neural Networks

https://github.com/graphdeeplearning/graphtransformer

공식 코드

A Generalization of Transformer Networks to Graphs

https://github.com/hamed1375/exphormer

공식 코드

Exphormer: Sparse Transformers for Graphs

https://github.com/hysonlab/multires-graph-transformer

공식 코드

Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures

https://github.com/ihollywhy/FactorGCN.PyTorch

공식 코드

Factorizable Graph Convolutional Networks

https://github.com/inria-thoth/csa

공식 코드

Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers

https://github.com/jeongwhanchoi/gfsa

공식 코드

Graph Convolutions Enrich the Self-Attention in Transformers!

https://github.com/jeongwhanchoi/panda

공식 코드

PANDA: Expanded Width-Aware Message Passing Beyond Rewiring

https://github.com/jiaruifeng/n2gnn

공식 코드

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

https://github.com/jw9730/hot

공식 코드

Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs

https://github.com/jw9730/lps

공식 코드

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

https://github.com/jw9730/tokengt

공식 코드

Pure Transformers are Powerful Graph Learners

https://github.com/jz48/regexplainer

공식 코드

RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks

https://github.com/karl-zhao/benchmarking-gnns-pyg

공식 코드

Benchmarking Graph Neural Networks

https://github.com/karolismart/dropgnn

공식 코드

DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

https://github.com/kbogas/PAM_BoP

공식 코드

From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis

https://github.com/kleincup/MGMN

공식 코드

Multilevel Graph Matching Networks for Deep Graph Similarity Learning

https://github.com/leemingo/tigt

공식 코드

Topology-Informed Graph Transformer

https://github.com/leichen2018/Ring-GNN

공식 코드

On the equivalence between graph isomorphism testing and function approximation with GNNs

https://github.com/lenscloth/grpe

공식 코드

GRPE: Relative Positional Encoding for Graph Transformer

https://github.com/liamma/grit

공식 코드

Graph Inductive Biases in Transformers without Message Passing

https://github.com/liugangcode/GREA

공식 코드

Graph Rationalization with Environment-based Augmentations

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.