Chapter 11. Junction Tree Variational Autoencoder for Molecular Graph Generation

2020 ◽  
pp. 228-249
Author(s):  
Wengong Jin ◽  
Regina Barzilay ◽  
Tommi Jaakkola
Keyword(s):  
Molecular Graph ◽  
Junction Tree ◽  
Variational Autoencoder ◽  
Graph Generation

scholarly journals Efficient learning of non-autoregressive graph variational autoencoders for molecular graph generation

2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Youngchun Kwon ◽  
Jiho Yoo ◽  
Youn-Suk Choi ◽  
Won-Joon Son ◽  
Dongseon Lee ◽  
...  
Keyword(s):  
Graph Matching ◽  
Molecular Graph ◽  
Generative Models ◽  
Molecular Graphs ◽  
Variational Autoencoder ◽  
Low Performance ◽  
Improved Learning ◽  
Graph Neural Networks ◽  
Efficient Learning ◽  
Graph Generation

AbstractWith the advancements in deep learning, deep generative models combined with graph neural networks have been successfully employed for data-driven molecular graph generation. Early methods based on the non-autoregressive approach have been effective in generating molecular graphs quickly and efficiently but have suffered from low performance. In this paper, we present an improved learning method involving a graph variational autoencoder for efficient molecular graph generation in a non-autoregressive manner. We introduce three additional learning objectives and incorporate them into the training of the model: approximate graph matching, reinforcement learning, and auxiliary property prediction. We demonstrate the effectiveness of the proposed method by evaluating it for molecular graph generation tasks using QM9 and ZINC datasets. The model generates molecular graphs with high chemical validity and diversity compared with existing non-autoregressive methods. It can also conditionally generate molecular graphs satisfying various target conditions.

scholarly journals Compressed graph representation for scalable molecular graph generation

2020 ◽  
Vol 12 (1) ◽  
Author(s):  
Youngchun Kwon ◽  
Dongseon Lee ◽  
Youn-Suk Choi ◽  
Kyoham Shin ◽  
Seokho Kang
Keyword(s):  
Deep Learning ◽  
Molecular Graph ◽  
Information Loss ◽  
Graph Representation ◽  
Compression Method ◽  
Large Molecules ◽  
Heavy Atoms ◽  
Additional Edge ◽  
Edge Features ◽  
Graph Generation

Abstract Recently, deep learning has been successfully applied to molecular graph generation. Nevertheless, mitigating the computational complexity, which increases with the number of nodes in a graph, has been a major challenge. This has hindered the application of deep learning-based molecular graph generation to large molecules with many heavy atoms. In this study, we present a molecular graph compression method to alleviate the complexity while maintaining the capability of generating chemically valid and diverse molecular graphs. We designate six small substructural patterns that are prevalent between two atoms in real-world molecules. These relevant substructures in a molecular graph are then converted to edges by regarding them as additional edge features along with the bond types. This reduces the number of nodes significantly without any information loss. Consequently, a generative model can be constructed in a more efficient and scalable manner with large molecules on a compressed graph representation. We demonstrate the effectiveness of the proposed method for molecules with up to 88 heavy atoms using the GuacaMol benchmark.

Investor-State Dispute Settlement under NAFTA Chapter 11: The Shape of Things to Come?

1998 ◽  
Vol 35 ◽  
pp. 263-290
Author(s):  
J. Anthony VanDuzer
Keyword(s):  
Free Trade Agreement ◽  
Dispute Settlement ◽  
Trade Agreement ◽  
Minimum Standards ◽  
The North ◽  
State Behaviour ◽  
Nafta Chapter 11 ◽  
To Come ◽  
The Right

SummaryRecently, there has been a proliferation of international agreements imposing minimum standards on states in respect of their treatment of foreign investors and allowing investors to initiate dispute settlement proceedings where a state violates these standards. Of greatest significance to Canada is Chapter 11 of the North American Free Trade Agreement, which provides both standards for state behaviour and the right to initiate binding arbitration. Since 1996, four cases have been brought under Chapter 11. This note describes the Chapter 11 process and suggests some of the issues that may arise as it is increasingly resorted to by investors.

Preventive Debt Restructuring and the Nigerian Draft Insolvency Legislation: Lessons from a Comparative Perspective

2020 ◽  
Vol 28 (1) ◽  
pp. 66-84
Author(s):  
Sanford U. Mba
Keyword(s):  
European Union ◽  
Economic Crisis ◽  
Final Analysis ◽  
The European Union ◽  
Debt Restructuring ◽  
The Us ◽  
Financially Distressed ◽  
Bankruptcy Code ◽  
Second Chance

Recently, the Nigerian Senate passed the Bankruptcy and Insolvency (Repeal and Re-enactment) Bill. This is no doubt a welcome development following the continued demand by insolvency practitioners, academics and other stakeholders for such legislation. The call has not only been for the enactment of just about any legislation, but (consistent with the economic challenges faced by businesses in the country), one that is favourably disposed to the successful restructuring of financially distressed businesses, allowing them to weather the storm of (impending) insolvency, emerge from it and continue to operate within the economy. This article seeks to situate this draft legislative instrument within the present wave of preventive restructuring ably espoused in the European Union Recommendation on New Approaches to Business Rescue and to Give Entrepreneurs a Second Chance (2014), which itself draws largely from Chapter 11 of the US Bankruptcy Code. The article draws a parallel between the economic crisis that gave rise to the preventive restructuring approach of the Recommendation and the present economic situation in Nigeria; it then examines the chances of such restructuring under the Nigerian draft bankruptcy and insolvency legislation. It argues in the final analysis that the draft legislation does not provide for a prophylactic recourse regime for financially distressed businesses. Consequently, a case is made for such an approach.

Sign in / Sign up

Export Citation Format

Share Document