Neural Architecture Search (NAS) is a promising and rapidly evolving research area. Training a large number of neural networks requires an exceptional amount of computational power, which makes NAS unreachable for those researchers who have limited or no access to high-performance clusters and supercomputers. A few benchmarks with precomputed neural architectures performances have been recently introduced to overcome this problem and ensure reproducible experiments. However, these benchmarks are only for the computer vision domain and, thus, are built from the image datasets and convolution-derived architectures. In this work, we step outside the computer vision domain by leveraging the language modeling task, which is the core of natural language processing (NLP). Our main contribution is as follows: we have provided search space of recurrent neural networks on the text datasets and trained 14k architectures within it; we have conducted both intrinsic and extrinsic evaluation of the trained models using datasets for semantic relatedness and language understanding evaluation; finally, we have tested several NAS algorithms to demonstrate how the precomputed results can be utilized. We consider that the benchmark will provide more reliable empirical findings in the community and stimulate progress in developing new NAS methods well suited for recurrent architectures. 

/pdf/nas-bench-nlp-neural-architecture-search-benchmark-for-2ceb4h8n.pdf

NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers need to enforce the use of general techniques, the use of sample-efficient methods, and the reproducibility of the results. While beneficial for the research community, these restrictions come at a cost -- increased difficulty. If the barrier for entry is too high, many potential participants are demoralized. With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers. With this track and more extensive tutorials and support, we saw an increased number of submissions. The participants of this easier track were able to obtain a diamond, and the participants of the harder track progressed the generalizable solutions in the same task.

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

http://manuscript.elsevier.com/S0008884622000503/pdf/S0008884622000503.pdf

Atomistic simulations of ettringite and its aqueous interfaces: Structure and properties revisited with the modified ClayFF force field

Polyethers are promising compounds for the creation of electrochemical energy storage systems. The molecular dynamics method can facilitate the search of compounds that have the most potential. However, the application of this method requires verification of the force fields. We perform molecular dynamics calculations of the physical properties of the aqueous 1,4-dioxane solution (density, enthalpy of mixing, and viscosity) and compare them to the available experimental data. In addition, we confirm the idea that the solution structure depends on the dioxane molar fraction, proposed in the experiment of Takamuku et al. [J. Mol. Liq. 83(1-3), 163–177 (1999)]. The hydrogen bonds between dioxane and water are analyzed. The correlation between the excess viscosity and enthalpy of mixing is demonstrated.

Properties of aqueous 1,4-dioxane solution via molecular dynamics.

We present the shared task on artificial text detection in Russian, which is organized as a part of the Dialogue Evaluation initiative, held in 2022. The shared task dataset includes texts from 14 text generators, i.e., one human writer and 13 text generative models fine-tuned for one or more of the following generation tasks: machine translation, paraphrase generation, text summarization, text simplification. We also consider back-translation and zero-shot generation approaches. The human-written texts are collected from publicly available resources across multiple domains. The shared task consists of two sub-tasks: (i) to determine if a given text is automatically generated or written by a human; (ii) to identify the author of a given text. The first task is framed as a binary classification problem. The second task is a multi-class classification problem. We provide count-based and BERT-based baselines, along with the human evaluation on the first sub-task. A total of 30 and 8 systems have been submitted to the binary and multi-class sub-tasks, correspondingly. Most teams outperform the baselines by a wide margin. We publicly release our codebase, human evaluation results, and other materials in our GitHub repository.

Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in Russian

The National Research University Higher School of Economics launched its HPC cluster and created a new division named the Supercomputer Simulation Unit. Now the university HPC cluster occupies seventh place in rating the most powerful computers of the CIS TOP50. The HPC cluster uses to solve machine learning problems, population genomics, hydrodynamics, atomistic and continuous modeling in physics, generative probabilistic models, financial row forecasting algorithms, and other actual problems. Paper describes the HSE HPC resources and experience of their use for scientific and educational tasks.

/pdf/hpc-resources-of-the-higher-school-of-economics-58dlbq2vis.pdf

P. S. Kostenetskiy

Papers

HPC Resources of the Higher School of Economics