This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding methods do not scale for real world information networks which usually contain millions of nodes. In this paper, we propose a novel network embedding method called the "LINE," which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted. The method optimizes a carefully designed objective function that preserves both the local and global network structures. An edge-sampling algorithm is proposed that addresses the limitation of the classical stochastic gradient descent and improves both the effectiveness and the efficiency of the inference. Empirical experiments prove the effectiveness of the LINE on a variety of real-world information networks, including language networks, social networks, and citation networks. The algorithm is very efficient, which is able to learn the embedding of a network with millions of vertices and billions of edges in a few hours on a typical single machine. The source code of the LINE is available online. 1
Glioblastomas are highly lethal cancers, containing self-renewing glioblastoma stem cells (GSC). Here, we show that GSCs, differentiated glioblastoma cells (DGC), and nonmalignant brain cultures all displayed robust circadian rhythms, yet GSCs alone displayed exquisite dependence on core clock transcription factors, BMAL1 and CLOCK, for optimal cell growth. Downregulation of BMAL1 or CLOCK in GSCs induced cell-cycle arrest and apoptosis. Chromatin immunoprecipitation revealed that BMAL1 preferentially bound metabolic genes and was associated with active chromatin regions in GSCs compared with neural stem cells. Targeting BMAL1 or CLOCK attenuated mitochondrial metabolic function and reduced expression of tricarboxylic acid cycle enzymes. Small-molecule agonists of two independent BMAL1-CLOCK negative regulators, the cryptochromes and REV-ERBs, downregulated stem cell factors and reduced GSC growth. Combination of cryptochrome and REV-ERB agonists induced synergistic antitumor effi cacy. Collectively, these fi ndings show that GSCs co-opt circadian regulators beyond canonical circadian circuitry to promote stemness maintenance and metabolism, offering novel therapeutic paradigms. SIGNIFICANCE:Cancer stem cells are highly malignant tumor-cell populations. We demonstrate that GSCs selectively depend on circadian regulators, with increased binding of the regulators in active chromatin regions promoting tumor metabolism. Supporting clinical relevance, pharmacologic targeting of circadian networks specifi cally disrupted cancer stem cell growth and self-renewal.
Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This paper proposes Recurrent Event Network (RE-NET), a novel autoregressive architecture for predicting future interactions. The occurrence of a fact (event) is modeled as a probability distribution conditioned on temporal sequences of past knowledge graphs. Specifically, our RE-NET employs a recurrent event encoder to encode past facts, and uses a neighborhood aggregator to model the connection of facts at the same timestamp. Future facts can then be inferred in a sequential manner based on the two modules. We evaluate our proposed method via link prediction at future times on five public datasets. Through extensive experiments, we demonstrate the strength of RE-NET, especially on multi-step inference over future timestamps, and achieve state-of-the-art performance on all five datasets 1 .
Distant supervision has been widely used in current systems of fine-grained entity typing to automatically assign categories (entity types) to entity mentions. However, the types so obtained from knowledge bases are often incorrect for the entity mention's local context. This paper proposes a novel embedding method to separately model "clean" and "noisy" mentions, and incorporates the given type hierarchy to induce loss functions. We formulate a joint optimization problem to learn embeddings for mentions and typepaths, and develop an iterative algorithm to solve the problem. Experiments on three public datasets demonstrate the effectiveness and robustness of the proposed method, with an average 15% improvement in accuracy over the next best compared method 1 .
Learning distributed node representations in networks has been a racting increasing a ention recently due to its e ectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which de nes a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with multiple views.is paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across di erent views. We propose a multi-view representation learning approach, which promotes the collaboration of di erent views and lets them vote for the robust representations. During the voting process, an a ention mechanism is introduced, which enables each node to focus on the most informative views. Experimental results on real-world networks show that the proposed approach outperforms existing state-of-theart approaches for network representation learning with a single view and other competitive approaches with multiple views.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.