arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.01162cs.LGcs.AI
收藏

DINE: 节点嵌入的维度可解释性

DINE: Dimensional Interpretability of Node Embeddings

University of Pisa(比萨大学);CENTAI Institute(CENTAI研究所);TU Delft(代尔夫特理工大学)

Simone Piaggesi, Megha Khosla, André Panisson, Avishek Anand

AI总结:

针对节点嵌入全局可解释性缺失的问题,提出衡量嵌入维度全局可解释性的新指标,并推出DINE方法,可在不损失任务性能的前提下提升现有节点嵌入的可解释性,实验验证了其在链路预测中的有效性。

摘要:

图因其能灵活地将社会和技术系统表示为由交互元素构成的网络而无处不在。图表示学习方法(例如节点嵌入)是将节点映射到潜在向量空间的强大方法,可用于各类图任务。尽管这类方法取得了成功,但仅有少数研究聚焦于对节点嵌入进行局部解释。此外,节点嵌入的全局解释仍处于未探索状态,限制了可解释性和调试潜力。我们通过为节点嵌入的各维度构建人类可理解的解释来填补这一空白。为此,我们首先基于嵌入维度对预测图结构的边际贡献,提出了衡量嵌入向量全局可解释性的新指标。我们认为,若一个嵌入维度能忠实地映射到输入图中可理解的子结构(例如社区结构),则该维度的可解释性更高。在观察到标准节点嵌入的可解释性较低后,我们提出了DINE(基于维度的可解释节点嵌入),这是一种可对现有节点嵌入进行改造的新方法,能在不牺牲任务性能的前提下提升其可解释性。我们在合成图和真实世界图上开展了大量实验,结果表明我们能同时学习到高可解释性的节点嵌入,且在链路预测任务中具备有效性能。

英文摘要:

Graphs are ubiquitous due to their flexibility in representing social and technological systems as networks of interacting elements. Graph representation learning methods, such as node embeddings, are powerful approaches to map nodes into a latent vector space, allowing their use for various graph tasks. Despite their success, only few studies have focused on explaining node embeddings locally. Moreover, global explanations of node embeddings remain unexplored, limiting interpretability and debugging potentials. We address this gap by developing human-understandable explanations for dimensions in node embeddings. Towards that, we first develop new metrics that measure the global interpretability of embedding vectors based on the marginal contribution of the embedding dimensions to predicting graph structure. We say that an embedding dimension is more interpretable if it can faithfully map to an understandable sub-structure in the input graph - like community structure. Having observed that standard node embeddings have low interpretability, we then introduce DINE (Dimension-based Interpretable Node Embedding), a novel approach that can retrofit existing node embeddings by making them more interpretable without sacrificing their task performance. We conduct extensive experiments on synthetic and real-world graphs and show that we can simultaneously learn highly interpretable node embeddings with effective performance in link prediction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑