More Like this

1. Ramsey theory of homogeneous structures: current trends and open problems

   Dobrinen, Natasha (December 2023, EMS Press)

   Baliaev, D; Smirnov, S (Ed.)

   This article highlights historical achievements in the partition theory of countable homogeneous relational structures, and presents recent work, current trends, and open problems. Exciting recent developments include new methods involving logic, topological Ramsey spaces, and category theory. The paper concentrates on big Ramsey degrees, presenting their essential structure where known and outlining areas for further development. Cognate areas, including infinite dimensional Ramsey theory of homogeneous structures and partition theory of uncountable structures are also discussed. 

   more » « less
2. Task-Guided Pair Embedding in Heterogeneous Network

   https://doi.org/10.1145/3357384.3357982  

   Park, Chanyoung; Kim, Donghyun; Zhu, Qi; Han, Jiawei; Yu, Hwanjo (November 2019, Proceedings of the 28th {ACM} International Conference on Information and Knowledge Management, {CIKM} 2019)

   Many real-world tasks solved by heterogeneous network embedding methods can be cast as modeling the likelihood of a 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 taskguided 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. 

   more » « less
3. A Dataset and an Approach for Identity Resolution of 38 Million Author IDs extracted from 2B Git Commits

   https://doi.org/10.1145/3379597.3387500  

   fry, tanner; dey, tapajit; Karnauch, Andrey; mockus, Audris (June 2020, IEEE International Working Conference on Mining Software Repositories)

   The data collected from open source projects provide means to model large software ecosystems, but often suffer from data quality issues, specifically, multiple author identification strings in code commits might actually be associated with one developer. While many methods have been proposed for addressing this problem, they are either heuristics requiring manual tweaking, or require too much calculation time to do pairwise comparisons for 38M author IDs in, for example, the World of Code collection. In this paper, we propose a method that finds all author IDs belonging to a single developer in this entire dataset, and share the list of all author IDs that were found to have aliases. To do this, we first create blocks of potentially connected author IDs and then use a machine learning model to predict which of these potentially related IDs belong to the same developer. We processed around 38 million author IDs and found around 14.8 million IDs to have an alias, which belong to 5.4 million different developers, with the median number of aliases being 2 per developer. This dataset can be used to create more accurate models of developer behaviour at the entire OSS ecosystem level and can be used to provide a service to rapidly resolve new author IDs. 

   more » « less
4. Mechanical cloak via data-driven aperiodic metamaterial design

   https://doi.org/10.1073/pnas.2122185119  

   Wang, Liwei; Boddapati, Jagannadh; Liu, Ke; Zhu, Ping; Daraio, Chiara; Chen, Wei (March 2022, Proceedings of the National Academy of Sciences)

   Mechanical cloaks are materials engineered to manipulate the elastic response around objects to make them indistinguishable from their homogeneous surroundings. Typically, methods based on material-parameter transformations are used to design optical, thermal, and electric cloaks. However, they are not applicable in designing mechanical cloaks, since continuum-mechanics equations are not form invariant under general coordinate transformations. As a result, existing design methods for mechanical cloaks have so far been limited to a narrow selection of voids with simple shapes. To address this challenge, we present a systematic, data-driven design approach to create mechanical cloaks composed of aperiodic metamaterials using a large precomputed unit cell database. Our method is flexible to allow the design of cloaks with various boundary conditions, multiple loadings, different shapes and numbers of voids, and different homogeneous surroundings. It enables a concurrent optimization of both topology and properties distribution of the cloak. Compared to conventional fixed-shape solutions, this results in an overall better cloaking performance and offers unparalleled versatility. Experimental measurements on additively manufactured structures further confirm the validity of the proposed approach. Our research illustrates the benefits of data-driven approaches in quickly responding to new design scenarios and resolving the computational challenge associated with multiscale designs of functional structures. It could be generalized to accommodate other applications that require heterogeneous property distribution, such as soft robots and implants design. 

   more » « less
5. Hybrid Deep Pairwise Classification for Author Name Disambiguation

   Kunho Kim, Shaurya Rohatgi (November 2019, 28th ACM International Conference on Information and Knowledge Management, CIKM 2019)

   Author name disambiguation (AND) can be defined as the problem of clustering together unique authors from all author mentions that have been extracted from publication or related records in digital libraries or other sources. Pairwise classification is an essential part of AND, and is used to estimate the probability that any pair of author mentions belong to the same author. Previous studies trained classifiers with features manually extracted from each attribute of the data. Recently, others trained a model to learn a vector representation from text without considering any structure information. Both of these approaches have advantages. The former method takes advantage of the structure of data, while the latter takes into account the textual similarity across attributes. Here, we introduce a hybrid method which takes advantage of both approaches by extracting both structure-aware features and global features. In addition, we introduce a novel way to train a global model utilizing a large number of negative samples. Results on AMiner and PubMed data shows the relative improvement of the mean average precision (MAP) by more than 7.45% when compared to previous state-of-the-art methods. 

   more » « less