FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2911591567> ?p ?o ?g. }

• W2911591567 abstract "A graph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines and there is a natural desire for understanding such data better. Deep learning (DL) has achieved significant breakthroughs in a variety of machine learning tasks in recent years, especially where data is structured on a grid, such as in text, speech, or image understanding. However, surprisingly little has been done to explore the applicability of DL on arbitrary graph-structured data directly. The goal of this thesis is to investigate architectures for DL on graphs and study how to transfer, adapt or generalize concepts that work well on sequential and image data to this domain. We concentrate on two important primitives: embedding graphs or their nodes into a continuous vector space representation (encoding) and, conversely, generating graphs from such vectors back (decoding). To that end, we make the following contributions. First, we introduce Edge-Conditioned Convolutions (ECC), a convolution-like operation on graphs performed in the spatial domain where filters are dynamically generated based on edge attributes. The method is used to encode graphs with arbitrary and varying structure. Second, we propose SuperPoint Graph, an intermediate point cloud representation with rich edge attributes encoding the contextual relationship between object parts. Based on this representation, ECC is employed to segment large-scale point clouds without major sacrifice in fine details. Third, we present GraphVAE, a graph generator allowing us to decode graphs with variable but upper-bounded number of nodes making use of approximate graph matching for aligning the predictions of an autoencoder with its inputs. The method is applied to the task of molecule generation." @default.
• W2911591567 created "2019-02-21" @default.
• W2911591567 creator A5026733401 @default.
• W2911591567 date "2019-01-24" @default.
• W2911591567 modified "2023-09-27" @default.
• W2911591567 title "Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back." @default.
• W2911591567 cites W1487641199 @default.
• W2911591567 cites W1497214886 @default.
• W2911591567 cites W1501565421 @default.
• W2911591567 cites W1560724230 @default.
• W2911591567 cites W1577931413 @default.
• W2911591567 cites W1644641054 @default.
• W2911591567 cites W1710476689 @default.
• W2911591567 cites W1836465849 @default.
• W2911591567 cites W1903029394 @default.
• W2911591567 cites W1903208982 @default.
• W2911591567 cites W1920022804 @default.
• W2911591567 cites W1932847118 @default.
• W2911591567 cites W1934027668 @default.
• W2911591567 cites W1959608418 @default.
• W2911591567 cites W196214544 @default.
• W2911591567 cites W1965555277 @default.
• W2911591567 cites W1973644502 @default.
• W2911591567 cites W1976257805 @default.
• W2911591567 cites W1983193888 @default.
• W2911591567 cites W1988115241 @default.
• W2911591567 cites W1990600049 @default.
• W2911591567 cites W2003447360 @default.
• W2911591567 cites W2008620264 @default.
• W2911591567 cites W2008857988 @default.
• W2911591567 cites W2016589492 @default.
• W2911591567 cites W2022153165 @default.
• W2911591567 cites W2022512855 @default.
• W2911591567 cites W2027482274 @default.
• W2911591567 cites W2043045881 @default.
• W2911591567 cites W2075638098 @default.
• W2911591567 cites W2079272365 @default.
• W2911591567 cites W2080635178 @default.
• W2911591567 cites W2092750499 @default.
• W2911591567 cites W2099405522 @default.
• W2911591567 cites W2101297579 @default.
• W2911591567 cites W2101491865 @default.
• W2911591567 cites W2102492119 @default.
• W2911591567 cites W2111160863 @default.
• W2911591567 cites W2112796928 @default.
• W2911591567 cites W2114244473 @default.
• W2911591567 cites W2116341502 @default.
• W2911591567 cites W2118246710 @default.
• W2911591567 cites W2124592697 @default.
• W2911591567 cites W2127911825 @default.
• W2911591567 cites W2131396337 @default.
• W2911591567 cites W2135024229 @default.
• W2911591567 cites W2135957668 @default.
• W2911591567 cites W2142498761 @default.
• W2911591567 cites W2143516773 @default.
• W2911591567 cites W2145131285 @default.
• W2911591567 cites W2147286743 @default.
• W2911591567 cites W2152864241 @default.
• W2911591567 cites W2156718197 @default.
• W2911591567 cites W2157331557 @default.
• W2911591567 cites W2159080219 @default.
• W2911591567 cites W2159213092 @default.
• W2911591567 cites W2163227453 @default.
• W2911591567 cites W2163922914 @default.
• W2911591567 cites W2171481071 @default.
• W2911591567 cites W2172859194 @default.
• W2911591567 cites W2173520492 @default.
• W2911591567 cites W2188365844 @default.
• W2911591567 cites W2194775991 @default.
• W2911591567 cites W2211722331 @default.
• W2911591567 cites W2259160646 @default.
• W2911591567 cites W2267126114 @default.
• W2911591567 cites W2299115575 @default.
• W2911591567 cites W2309415944 @default.
• W2911591567 cites W2333621733 @default.
• W2911591567 cites W2346698422 @default.
• W2911591567 cites W2401971606 @default.
• W2911591567 cites W2405756170 @default.
• W2911591567 cites W2414711238 @default.
• W2911591567 cites W2431962807 @default.
• W2911591567 cites W2460657278 @default.
• W2911591567 cites W2468480579 @default.
• W2911591567 cites W2473418274 @default.
• W2911591567 cites W2522528264 @default.
• W2911591567 cites W2524838846 @default.
• W2911591567 cites W2527189750 @default.
• W2911591567 cites W2533800772 @default.
• W2911591567 cites W2552391307 @default.
• W2911591567 cites W2554952599 @default.
• W2911591567 cites W2556802233 @default.
• W2911591567 cites W2556833785 @default.
• W2911591567 cites W2558460151 @default.
• W2911591567 cites W2558748708 @default.
• W2911591567 cites W2560609797 @default.
• W2911591567 cites W2560722161 @default.
• W2911591567 cites W2565378226 @default.
• W2911591567 cites W2578240541 @default.
• W2911591567 cites W2579549467 @default.
• W2911591567 cites W2581376856 @default.
• W2911591567 cites W2591711955 @default.

• next