While self-supervised graph pretraining techniques have shown promising
results in various domains, their application still experiences challenges of
limited topology learning, human knowledge dependency, and incompetent
multi-level interactions. To address these issues, we propose a novel solution,
Dual-level Graph self-supervised Pretraining with Motif discovery (DGPM), which
introduces a unique dual-level pretraining structure that orchestrates
node-level and subgraph-level pretext tasks. Unlike prior approaches, DGPM
autonomously uncovers significant graph motifs through an edge pooling module,
aligning learned motif similarities with graph kernel-based similarities. A
cross-matching task enables sophisticated node-motif interactions and novel
representation learning. Extensive experiments on 15 datasets validate DGPM's
effectiveness and generalizability, outperforming state-of-the-art methods in
unsupervised representation learning and transfer learning settings. The
autonomously discovered motifs demonstrate the potential of DGPM to enhance
robustness and interpretability.

我们提出了一种新颖的解决方案，双层图自监督预训练与图形模体发现（DGPM），通过引入独特的双层预训练结构来解决拓扑学习有限，依赖人类知识和多级交互无力等挑战。在 15 个数据集上的大量实验证实了 DGPM 的有效性和普适性，在无监督表示学习和迁移学习设置中优于最先进的方法。自主发现的模体展示了 DGPM 提升鲁棒性和可解释性的潜力。

提升双层图自我监督预训练，结合模式发现

Empowering Dual-Level Graph Self-Supervised Pretraining with Motif  Discovery

Video-based person re-identification aims to match pedestrians from video
sequences across non-overlapping camera views. The key factor for video person
re-identification is to effectively exploit both spatial and temporal clues
from video sequences. In this work, we propose a novel Spatial-Temporal
Correlation and Topology Learning framework (CTL) to pursue discriminative and
robust representation by modeling cross-scale spatial-temporal correlation.
Specifically, CTL utilizes a CNN backbone and a key-points estimator to extract
semantic local features from human body at multiple granularities as graph
nodes. It explores a context-reinforced topology to construct multi-scale
graphs by considering both global contextual information and physical
connections of human body. Moreover, a 3D graph convolution and a cross-scale
graph convolution are designed, which facilitate direct cross-spacetime and
cross-scale information propagation for capturing hierarchical spatial-temporal
dependencies and structural information. By jointly performing the two
convolutions, CTL effectively mines comprehensive clues that are complementary
with appearance information to enhance representational capacity. Extensive
experiments on two video benchmarks have demonstrated the effectiveness of the
proposed method and the state-of-the-art performance.

本文提出了一种新的 CTL 框架来实现视频行人重新识别，其通过建模跨尺度时空相关性来追求具有辨别力和鲁棒性的表征，采用了卷积神经网络和关键点估计器来抽取人体的语义局部特征，并通过构建多尺度图形来捕捉分层时空依赖性和结构信息，最终证明了该方法在两个视频基准上实现了最先进的表现。