Domain-specific hierarchical subgraph extraction: A recommendation use case

Lalithsena, Sarasi; Perera, Sujan; Kapanipathi, Pavan; Sheth, Amit P.

doi:10.1109/bigdata.2017.8257982

Cited by 10 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the example in Figure 1, we extract a subgraph that includes the purple nodes because they are directly connected to green and/or blue nodes. Personalized PageRank (PPR) to Filter Context: KGs are typically very large, and concept expansion by just one hop can introduce a significant amount of noise Lalithsena et al 2017). For example, the concept girl is directly connected to over 1000 other concepts in ConceptNet.…”

Section: Subgraph Extractionmentioning

confidence: 99%

Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks

Kapanipathi¹,

Thost²,

Patel³

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

Textual entailment is a fundamental task in natural language processing. Most approaches for solving this problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task. However, the proposed models do not fully exploit the information in the usually large and noisy KGs, and it is not clear how it can be effectively encoded to be useful for entailment. We present an approach that complements text-based entailment models with information from KGs by (1) using Personalized PageRank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture the structural and semantic information in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps the model to be robust and improves prediction accuracy. This is particularly evident in the challenging BreakingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models.

show abstract

Section: Subgraph Extractionmentioning

confidence: 99%

Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks

Kapanipathi¹,

Thost²,

Patel³

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Challenge 5: Quality and Validity Of Kgsmentioning

confidence: 99%

“…The correctness of knowledge added to KGs also depend on its temporal validity. Temporally changing relationships to define the relatedness between entities to model domain-specific [10] and temporal multirelational data is another concern deserving significant attention. Challenge 6: Adaptive Knowledge Network Change is a law of nature, and static KGs like DBpedia fail to capture this dynamic flow of information.…”

Section: Challenge 5: Quality and Validity Of Kgsmentioning

confidence: 99%

Knowledge Graphs and Knowledge Networks: The Story in Brief

Sheth

Padhee

Gyrard

2019

IEEE Internet Comput.

Self Cite

View full text Add to dashboard Cite

Knowledge Graphs (KGs) represent real-world noisy raw information in a structured form, capturing relationships between entities. However, for dynamic real-world applications such as social networks, recommender systems, computational biology, relational knowledge representation has emerged as a challenging research problem where there is a need to represent the changing nodes, attributes, and edges over time. The evolution of search engine responses to user queries in the last few years is partly because of the role of KGs such as Google KG. KGs are significantly contributing to various AI applications from link prediction, entity relations prediction, node classification to recommendation and question answering systems. This article is an attempt to summarize the journey of KG for AI.

show abstract

“…While MLNs use discrete logic to construct a MRF over discrete random variables, PSL uses soft logic to construct a special kind of MRF over continuous random variables in range [0, 1] called a hinge-loss Markov random field (HLMRF). PSL and MLNs have achieved state-of-the-art results in various domains such as recommender systems (Kouki et al 2017;Lalithsena et al 2017;Choi et al 2015), bioinformatics (Sridhar et al 2016), natural language processing (Ebrahimi et al 2016;Johnson et al 2017;Khot et al 2015;Beltagy et al 2013), product search (Alshukaili et al 2016;Platanios et al 2017;Srinivasan et al 2019), fake news detection (Chowdhury et al 2020) and social network analysis (Farnadi et al 2017;Chen et al 2017).…”

Section: Introductionmentioning

confidence: 99%

A taxonomy of weight learning methods for statistical relational learning

et al. 2021

View full text Add to dashboard Cite

Statistical relational learning (SRL) frameworks are effective at defining probabilistic models over complex relational data. They often use weighted first-order logical rules where the weights of the rules govern probabilistic interactions and are usually learned from data. Existing weight learning approaches typically attempt to learn a set of weights that maximizes some function of data likelihood; however, this does not always translate to optimal performance on a desired domain metric, such as accuracy or F1 score. In this paper, we introduce a taxonomy of search-based weight learning approaches for SRL frameworks that directly optimize weights on a chosen domain performance metric. To effectively apply these search-based approaches, we introduce a novel projection, referred to as scaled space (SS), that is an accurate representation of the true weight space. We show that SS removes redundancies in the weight space and captures the semantic distance between the possible weight configurations. In order to improve the efficiency of search, we also introduce an approximation of SS which simplifies the process of sampling weight configurations. We demonstrate these approaches on two state-of-the-art SRL frameworks: Markov logic networks and probabilistic soft logic. We perform empirical evaluation on five real-world datasets and evaluate them each on two different metrics. We also compare them against four other weight learning approaches. Our experimental results show that our proposed search-based approaches outperform likelihood-based approaches and yield up to a 10% improvement across a variety of performance metrics. Further, we perform an extensive evaluation to measure the robustness of our approach to different initializations and hyperparameters. The results indicate that our approach is both accurate and robust.

show abstract

Domain-specific hierarchical subgraph extraction: A recommendation use case

Cited by 10 publications

References 17 publications

Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks

Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks

Knowledge Graphs and Knowledge Networks: The Story in Brief

A taxonomy of weight learning methods for statistical relational learning

Contact Info

Product

Resources

About