Citations of scientific papers and patents reveal the knowledge flow and usually serve as the metric for evaluating their novelty and impacts in the field. Citation Forecasting thus has various applications in the real world. Existing works on citation forecasting typically exploit the sequential properties of citation events, without exploring the citation network. In this paper, we propose to explore both the citation network and the related citation event sequences which provide valuable information for future citation forecasting. We propose a novel \em Citation Network and Event Sequence (CINES) Model to encode signals in the citation network and related citation event sequences into various types of embeddings for decoding to the arrivals of future citations. Moreover, we propose atemporal network attention and three alternative designs of \em bidirectional feature propagation to aggregate the retrospective and prospective aspects of publications in the citation network, coupled with the citation event sequence embeddings learned by a \em two-level attention mechanism for the citation forecasting. We evaluate our models and baselines on both a U.S. patent dataset and a DBLP dataset. Experimental results show that our models outperform the state-of-the-art methods, i.e., RMTPP, CYAN-RNN, Intensity-RNN, and PC-RNN, reducing the forecasting error by 37.76% - 75.32%.

Research suggests that social relationships have substantial impacts on individuals’ health outcomes. Network intervention, through careful planning, can assist a network of users to build healthy relationships. However, most previous work is not designed to assist such planning by carefully examining and improving multiple network characteristics. In this paper, we propose and evaluate algorithms that facilitate network intervention planning through simultaneous optimization of network degree, closeness, betweenness, and local clustering coefficient, under scenarios involving Network Intervention with Limited Degradation - for Single target (NILD-S) and Network Intervention with Limited Degradation - for Multiple targets (NILD-M). We prove that NILD-S and NILD-M are NP-hard and cannot be approximated within any ratio in polynomial time unless P=NP. We propose the Candidate Re-selection with Preserved Dependency (CRPD) algorithm for NILD-S, and the Objective-aware Intervention edge Selection and Adjustment (OISA) algorithm for NILD-M. Various pruning strategies are designed to boost the efficiency of the proposed algorithms. Extensive experiments on various real social networks collected from public schools and Web and an empirical study are conducted to show that CRPD and OISA outperform the baselines in both efficiency and effectiveness.

In this paper, we propose a novel representation learning framework, namely HIN2Vec, for heterogeneous information networks (HINs). The core of the proposed framework is a neural network model, also called HIN2Vec, designed to capture the rich semantics embedded in HINs by exploiting different types of relationships among nodes. Given a set of relationships specified in forms of meta-paths in an HIN, HIN2Vec carries out multiple prediction training tasks jointly based on a target set of relationships to learn latent vectors of nodes and meta-paths in the HIN. In addition to model design, several issues unique to HIN2Vec, including regularization of meta-path vectors, node type selection in negative sampling, and cycles in random walks, are examined. To validate our ideas, we learn latent vectors of nodes using four large-scale real HIN datasets, including Blogcatalog, Yelp, DBLP and U.S. Patents, and use them as features for multi-label node classification and link prediction applications on those networks. Empirical results show that HIN2Vec soundly outperforms the state-of-the-art representation learning models for network data, including DeepWalk, LINE, node2vec, PTE, HINE and ESim, by 6.6% to 23.8% of $micro$-$f_1$ in multi-label node classification and 5% to 70.8% of $MAP$ in link prediction.

The extant work on network analyses has thus far paid little attention to the heterogeneity in time lags and speed of information propagation along edges. In this paper, we study this novel problem, modeling the time dimension and lags on network edges, in the context of paper and patent citation networks where the variation in the speed of knowledge flows between connected nodes is apparent. We propose to model time lags in knowledge diffusions in citation networks in one of the two ways: deterministic lags and probabilistic lags. Then, we discuss two approaches of computationally working with time lags in edges of citation networks. Experimentally, we study two different applications to demonstrate the importance of the time dimension and lags in citations: (1) HITS algorithm and (2) patent citation recommendation. We conduct experiments on millions of U. S. patent data and Web of Science (WOS) paper data. Our experiments show that incorporating time dimension and lags in edges significantly improve network modeling and analyses.

There is a consensus that U. S. patent examiners, who are responsible for identifying prior art relevant to adjudicationof patentability of patent applications, often lack thetime, resources and/or experience necessary to conduct adequateprior art search. This study aims to build an automatic andeffective system of patent citation recommendation for patentexaminers. In addition to focusing on content and bibliographicinformation, our proposed system considers another importantpiece of information that is known by patent examiners, namely, applicant citations. We integrate applicant citations and bibliographicinformation of patents into a heterogeneous citationbibliographicnetwork. Based on this network, we explore metapathsbased relationships between a query patent application anda candidate prior patent and classify them into two categories:(1) Bibliographic meta-paths, (2) Applicant Bibliographic metapaths. We propose a framework based on a two-phase rankingapproach: the first phase involves selection of a candidate subsetfrom the whole U. S. patent data, and the second phase usessupervised learning models to rank prior patents in the candidatesubset. The results show that both bibliographic informationand applicant citation information are very useful for examinercitation recommendation, and that our approach significantlyoutperforms a search engine.

Effective patent valuation is important for patent holders. Forward patent citations, widely used in assessing patent value, have been considered as reflecting knowledge flows, just like paper citations. However, patent citations also carry legal implication, which is important for patent valuation. We argue that patent citations can either be technological citations that indicate knowledge transfer or be legal citations that delimit the legal scope of citing patents. In this paper, we first develop citation-network based methods to infer patent quality measures at either the legal or technological dimension. Then we propose a probabilistic mixture approach to incorporate both the legal and technological dimensions in patent citations, and an iterative learning process that integrates a temporal decay function on legal citations, a probabilistic citation network based algorithm and a prediction model for patent valuation. We learn all the parameters together and use them for patent valuation. We demonstrate the effectiveness of our approach by using patent maintenance status as an indicator of patent value and discuss the insights we learned from this study.

The U.S. recently adopted a post-grant opposition procedure to encourage third parties to challenge the validity of newly granted patents by providing relevant prior patents that are missed during patent examination (i.e., missing citations). In this paper, we propose a recommendation system for missing citations for newly granted patents. The recommendation system, based on the patent citation network of a newly granted query patent, focuses on paths that start with the references of the query patent in the network. Our approach is to identify the relevancy of a candidate patent to the query patent by its citation relationship (paths) that are distinguished based on the direction, topology and semantics of the paths in the network. We consider six different types of paths between a candidate patent and a query patent based on their citation relationship and define a relevancy score for each path type. Accordingly, we rank candidate patents via a RankSVM model learned by using those relevancy scores as features. The experimental results show our approach significantly improves the average precision and recall performance compared to two baseline methods, i.e., Katz distance and text similarity.

Patents are very important intangible assets that protect firm technologies and maintain market competitiveness. Thus, patent evaluation is critical for firm business strategy and innovation management. Currently patent evaluation mostly relies on some meta information of patents, such as number of forward/backward citations and number of claims. In this paper, we propose to identify patent technological trends, which carries information about technology evolution and trajectories among patents, to enable more effective and precise patent evaluation. We explore features to capture both the value of trends and the quality of patents within a trend, and perform patent evaluation to validate the extracted trends and features using patents in the United States Patent and Trademark Office (USPTO) dataset. Experimental results demonstrate that the identified technological trends are able to capture patent value precisely. With the proposed trend related features extracted from our identified trends, we can improve patent evaluation performance significantly over the baseline using conventional features.

Patent citation recommendation and prior patent search, critical for patent filing and patent examination, have become increasingly difficult due to the rapidly growing number of patents. Unlike paper citations that focus on reference comprehensiveness, patent citations tend to be more parsimonious and refer only to those prior patents bearing significant technological and/or economic value, as they define the scope of the citing patent and thus have significant legal and economic implications. Based on the insight that patent citations are important information reflecting the value of cited patents to the citing patent, we propose a heterogeneous patent citation-bibliographic network that combines patent citations (reflecting value relation) and bibliographic information (reflecting similarity relation) together. From this network, we extract various features that reflect the value of a prior patent to a query patent with regard to the context of the query patent such as its assignee, classifications, etc. We then propose a two-stage framework for patent citation recommendation. Our idea is that by exploiting those context-specific value measures of candidate patents to the query patent, the proposed framework is able to make effective patent citation recommendations. We evaluate the proposed context-guided value-driven framework using a collection of 1.8M U.S. patents. Experimental results validate our ideas and show that those value-driven features are very effective and significantly outperform two state-of-the-art methods in terms of both the precision and recall rates.