Many real-world tasks solved by heterogeneous network embedding methods can be cast as modeling the likelihood of pairwise relationship between two nodes. For example, the goal of author identification task is to model the likelihood of a paper being written by an author (paper-author pairwise relationship). Existing task-guided embedding methods are node-centric in that they simply measure the similarity between the node embeddings to compute the likelihood of a pairwise relationship between two nodes. However, we claim that for task-guided embeddings, it is crucial to focus on directly modeling the pairwise relationship. In this paper, we propose a novel task-guided pair embedding framework in heterogeneous network, called TaPEm, that directly models the relationship between a pair of nodes that are related to a specific task (e.g., paper-author relationship in author identification). To this end, we 1) propose to learn a pair embedding under the guidance of its associated context path, i.e., a sequence of nodes between the pair, and 2) devise the pair validity classifier to distinguish whether the pair is valid with respect to the specific task at hand. By introducing pair embeddings that capture the semantics behind the pairwise relationships, we are able to learn the fine-grained pairwise relationship between two nodes, which is paramount for task-guided embedding methods. Extensive experiments on author identification task demonstrate that TaPEm outperforms the state-of-the-art methods, especially for authors with few publication records.
Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning
State Key Laboratory for Novel Software Technology（计算机软件新技术国家重点实验室）；Nanjing University（南京大学）；National Institute of Healthcare Data Science（国家健康医疗数据科学研究院）
PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
Microsoft Research Asia（微软亚洲研究院）；Peking University（北京大学）；University of Michigan（密歇根大学）
无监督文本嵌入方法，如Skip-gram和Paragraph Vector，由于其简单性，可扩展性和有效性而受到越来越多的关注。然而，与复杂的深度学习架构（如卷积神经网络）相比，这些方法在应用于特定的机器学习任务时通常会产生较差的结果。一个可能的原因是，这些文本嵌入方法以完全无监督的方式学习文本的表示，而不利用可用于任务的标记信息。虽然学习的低维表示适用于许多不同的任务，但它们并不特别适合任何任务。在本文中，我们填补了这一空白，提出了一个半监督表示学习方法的文本数据，我们称之为\textit{predictive text embedding}（PTE）。预测文本嵌入利用标记和未标记的数据来学习文本的嵌入。首先将标注信息和不同层次的词共现信息表示为一个大规模的异构文本网络，然后通过一种有原则的高效算法将其嵌入到低维空间中。这种低维嵌入不仅保持了单词和文档的语义接近性，而且对特定任务具有很强的预测能力。与最近基于卷积神经网络的监督方法相比，预测文本嵌入相当或更有效，效率更高，并且需要调整的参数更少。
Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation
State Key Lab of CAD&CG（CAD与CG国家重点实验室）；School of Computing（计算机学院）；National University of Singapore（新加坡国立大学）；School of Intelligence Science and Engineering（智能科学与工程学院）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；National University of Singapore（新加坡国立大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）
