1st Workshop on Knowledge Injection in Neural Networks (KINN)

Workshop Website https://sites.google.com/view/kinn2021/home

Workshop Organisers

  • Vasudev Lal
    Intel Labs, USA
  • Somak Aditya
    Microsoft Research, India
  • Yezhou Yang
    ASU, USA
  • Pasquale Minervini
    UCL, UK
  • Sandya Mannarswamy
    Intel, India

Workshop Abstract

Deep learning (DL) has made rapid progress in the last decade, with neural network-based language and vision models achieving state-of-the-art performance in various tasks. Yet, purely data-driven neural network models exhibit several issues impacting real-world deployment of such models adversely. These include reliance on large quantities of training data, poor robustness, lack of generalization, poor explainability, and glaring gaps in implicit and commonsense knowledge. The availability of rich structured (or semi-structured) knowledge sources has spurred the research community into exploring Knowledge Injection in Neural Networks (KINN) as a means of mitigating the above-mentioned challenges. This has led to the development of hybrid AI systems that combine the purely data-driven learning of the neural network models with an infusion of knowledge from external sources. Such KINN systems include the development of retrieval augmented neural models, neuro symbolic systems and a plethora of combinations of NNs and knowledge graphs and structured knowledge bases.

Given the considerable promise of knowledge injection in overcoming the current challenges associated with purely data driven NN models, we propose a workshop on Knowledge Injection in Neural Networks (KINN) at CIKM 2021. The goal of this workshop is to focus the attention of the CIKM research community on addressing the open challenges in this emerging research area. Given that the CIKM research community has a rich mix of experts in structured knowledge representation, IR and DL, this workshop is intended to facilitate cross-disciplinary collaboration across the various CIKM research communities into building efficient and scalable KINN systems.