Zobrazeno 1 - 10
of 9 777
pro vyhledávání: '"A. A. Kharlamov"'
Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as t
Externí odkaz:
http://arxiv.org/abs/2410.22105
Autor:
Artemenkov, D. A., Bradnova, V., Britvich, G. I., Zaitsev, A. A., Zarubin, P. I., Zarubina, I. G., Kalinin, V. A., Kattabekov, R. R., Kornegrutsa, N. K., Kostin, M. Yu., Maksimov, A. V., Mamatkulov, K. Z., Mitseva, E., Neagu, A., Pikalov, V. A., Polkovnikov, M. K., Rukoyatkin, P. A., Rusakova, V. V., Sarkisyan, V. R., Stanoeva, R., Firu, E., Haiduc, M., Kharlamov, S. P.
Publikováno v:
Physics of Atomic Nuclei, 2017, Vol. 80, No. 6, pp. 1126-1132
The results obtained by estimating the contribution of $^8$Be and $^9$B nuclei to the coherent dissociation of $^{10}$C, $^{10}$B, and $^{12}$C relativistic nuclei in nuclear track emulsions (``white'' stars) are presented. The selection of ``white''
Externí odkaz:
http://arxiv.org/abs/2409.16164
We undertake a study of topological properties of the real Mordell-Weil group $\operatorname{MW}_{\mathbb R}$ of real rational elliptic surfaces $X$ which we accompany by a related study of real lines on $X$ and on the "subordinate" del Pezzo surface
Externí odkaz:
http://arxiv.org/abs/2409.01202
Autor:
Zhu, Yuqicheng, Potyka, Nico, Pan, Jiarong, Xiong, Bo, He, Yunjie, Kharlamov, Evgeny, Staab, Steffen
Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking a
Externí odkaz:
http://arxiv.org/abs/2408.08248
Autor:
Zhu, Yuqicheng, Potyka, Nico, Nayyeri, Mojtaba, Xiong, Bo, He, Yunjie, Kharlamov, Evgeny, Staab, Steffen
Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link prediction yet give conflicting predictions for unseen queries. This p
Externí odkaz:
http://arxiv.org/abs/2408.08226
Graph neural networks (GNNs) have achieved significant success in various applications. Most GNNs learn the node features with information aggregation of its neighbors and feature transformation in each layer. However, the node features become indist
Externí odkaz:
http://arxiv.org/abs/2407.19231
Autor:
Zhao, Huanjing, Yang, Beining, Cen, Yukuo, Ren, Junyu, Zhang, Chenhui, Dong, Yuxiao, Kharlamov, Evgeny, Zhao, Shu, Tang, Jie
The text-attributed graph (TAG) is one kind of important real-world graph-structured data with each node associated with raw texts. For TAGs, traditional few-shot node classification methods directly conduct training on the pre-processed node feature
Externí odkaz:
http://arxiv.org/abs/2407.15431
Autor:
SND Collaboration, Achasov, M. N., Barnyakov, A. Yu., Bedarev, E. V., Beloborodov, K. I., Berdyugin, A. V., Bogdanchikov, A. G., Botov, A. A., Chistyakov, D. E., Dimova, T. V., Druzhinin, V. P., Kardapoltsev, E. V., Kasaev, A. S., Kattsin, A. A., Kharlamov, A. G., Koop, I. A., Korol, A. A., Kovrizhin, D. P., Kupich, A. S., Kryukov, A. P., Melnikova, N. A., Muchnoi, N. Yu., Obrazovsky, A. E., Pakhtusova, E. V., Pugachev, K. V., Rastigeev, S. A., Rogovsky, Yu. A., Senchenko, A. I., Serednyakov, S. I., Shatunov, Yu. M., Sherstyuk, S. P., Shtol, D. A., Silagadze, Z. K., Surin, I. K., Usov, Yu. V., Zhabin, V. N., Zharinov, Yu. M.
The cross section for the $e^+e^-\to K_SK_L$ process is measured in the center-of-mass energy range from 1000 MeV to 1100 MeV in the experiment with the SND detector at the VEPP-2000 $e^+e^-$ collider. The measurement is carried out in the $K_S\to 2\
Externí odkaz:
http://arxiv.org/abs/2407.15140
Autor:
Zhu, Yuqicheng, Potyka, Nico, Xiong, Bo, Tran, Trung-Kien, Nayyeri, Mojtaba, Kharlamov, Evgeny, Staab, Steffen
Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard. We explain how knowledge graph embeddings can be used to approximate probabilistic inference efficiently using the example of Statistical EL (SEL), a s
Externí odkaz:
http://arxiv.org/abs/2407.11821
Autor:
He, Yunjie, Hernandez, Daniel, Nayyeri, Mojtaba, Xiong, Bo, Zhu, Yuqicheng, Kharlamov, Evgeny, Staab, Steffen
Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily
Externí odkaz:
http://arxiv.org/abs/2407.09212