Finding drug-drug interaction is crucial for patient safety and treatment efficacy. Two drugs may show a synergistic effect but may sometimes cause a severe health issue, including lethality. Wet lab studies are often performed to understand such interactions but are limited by cost and time. However, the biochemical data generated can be explored to compute unknown interactions. Here, we developed a computational model named UniGEN-DDI (Unified Graph Embedding Network for Drug-Drug Interaction) for the estimation of interactions between drugs. It is a simple unified network model containing the biochemical information of drug association developed using the compiled data from DrugBank 5.1.0. The feature learning of the drugs was carried out using a combination of GraphSAGE and Node2Vec algorithms, which were found efficient in extracting diverse features. The simple architecture of our model led to a significant reduction in computational time compared to the baselines, while maintaining a high prediction accuracy. The model performed well on the data, which was equally distributed between interacting and non-interacting drugs. As a more challenging evaluation, we performed non-overlapping splitting of the data based on the drug action on different parts of the body, and our model performed well in both interaction estimation and time efficiency. Our model successfully identified 15 previously unknown drug interactions in DrugBank 5.1.0 in the top 20 estimates (75% correct prediction), which were confirmed from experimental studies in updated DrugBank 6.0. In the top 50 estimates, 68% of the unknown drug interactions were correctly identified that showcased a strong performance of our model.

The increasing frequency of natural disasters has heightened the demand for UAV (Unmanned Aerial Vehicle) technologies. UAVs, especially drones, can monitor remote disaster areas and provide situational awareness to emergency responders. Equipped with cameras and onboard computers, drones can detect survivors in real-time, enhancing the efficiency of Search and Rescue (SAR) operations. Due to limited battery capacity, the drones must be deployed along a path of the shortest possible length to avoid delays in detecting the survivors in a given disaster area. Traditional path-planning algorithms struggle to address the dynamic conditions in disaster areas. We propose an adaptive drone path planning framework for real-time survivor detection in disaster areas to address this. This framework aims to improve survivor detection by guiding UAVs along routes with higher probabilities of the presence of survivors. Adopting a ”Learn-As-You-Go” strategy, it trains a Potential Survivor Location (PSL) prediction model to identify way-points for drone sorties. Next, it leverages a novel computationally efficient path planning approach called Prediction-Based Priority-Aware Path Planning (PB-PAPP) to navigate towards the identified PSLs. Also, we present a Weight Synthesis module that enhances the prediction quality over time by aggregating the weights of the models trained by the drones, allowing continuous adaptation in changing environments. Finally, we present a prototype lightweight decentralized machine learning system that combines the above modules to facilitate real-time survivor detection. Compared to existing algorithms, our framework demonstrates an 84-97% reduction in overhead for adaptive path-planning.

In the ever-evolving landscape of natural language processing and information retrieval, the need for robust and domain-specific entity linking algorithms has become increasingly apparent.It is crucial in a considerable number of fields such as humanities, technical writing and biomedical sciences to enrich texts with semantics and discover more knowledge.The use of Named Entity Disambiguation (NED) in such domains requires handling noisy texts, low resource settings and domain-specific KBs.Existing approaches are mostly inappropriate for such scenarios, as they either depend on training data or are not flexible enough to work with domain-specific KBs.Thus in this work, we present an unsupervised approach leveraging the concept of Group Steiner Trees (GST), which can identify the most relevant candidates for entity disambiguation using the contextual similarities across candidate entities for all the mentions present in a document.We outperform the state-of-the-art unsupervised methods by more than 40% (in avg.) in terms of Precision@1 across various domain-specific datasets.

Question answering over RDF data like knowledge graphs has been greatly advanced, with a number of good systems providing crisp answers for natural language questions or telegraphic queries. Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone. Conversely, the IR and NLP communities have addressed QA over text, but such systems barely utilize semantic data and knowledge. This paper presents a method for complex questions that can seamlessly operate over a mixture of RDF datasets and text corpora, or individual sources, in a unified framework. Our method, called Uniqorn , builds a context graph on-the-fly, by retrieving question-relevant evidences from the RDF data and/or a text corpus, using fine-tuned BERT models. The resulting graph typically contains all question-relevant evidences but also a lot of noise. Uniqorn copes with this input by a graph algorithm for Group Steiner Trees, that identifies the best answer candidates in the context graph. Experimental results on several benchmarks of complex questions with multiple entities and relations, show that Uniqorn significantly outperforms state-of-the-art methods for heterogeneous QA – in a full training mode, as well as in zero-shot settings. The graph-based methodology provides user-interpretable evidence for the complete answering process. • Unified method for answering complex questions over heterogeneous knowledge sources. • Two-stage pipeline where the first phase is supervised, and the second unsupervised. • Extensive evaluation with six benchmarks and ten baselines. • Zero-shot QA setup where pre-trained models must compete on held-out benchmarks. • Large-scale crowdsourced human evaluation with 86k annotations on answer correctness.

Question answering over knowledge graphs (KG-QA) is a vital topic in IR. Questions with temporal intent are a special class of practical importance, but have not received much attention in research. This work presents EXAQT, the first end-to-end system for answering complex temporal questions that have multiple entities and predicates, and associated temporal conditions. EXAQT answers natural language questions over KGs in two stages, one geared towards high recall, the other towards precision at top ranks. The first step computes question-relevant compact subgraphs within the KG, and judiciously enhances them with pertinent temporal facts, using Group Steiner Trees and fine-tuned BERT models. The second step constructs relational graph convolutional networks (R-GCNs) from the first step's output, and enhances the R-GCNs with time-aware entity embeddings and attention over temporal relations. We evaluate EXAQT on TimeQuestions, a large dataset of 16k temporal questions we compiled from a variety of general purpose KG-QA benchmarks. Results show that EXAQT outperforms three state-of-the-art systems for answering complex questions over KGs, thereby justifying specialized treatment of temporal QA.

System-provided explanations for recommendations are an important component towards transparent and trustworthy AI. In state-of-the-art research, this is a one-way signal, though, to improve user acceptance. In this paper, we turn the role of explanations around and investigate how they can contribute to enhancing the quality of generated recommendations themselves. We devise a human-in-the-loop framework, called Elixir, where user feedback on explanations is leveraged for pairwise learning of user preferences. Elixir leverages feedback on pairs of recommendations and explanations to learn user-specific latent preference vectors, overcoming sparseness by label propagation with item-similarity-based neighborhoods. Our framework is instantiated using generalized graph recommendation via Random Walk with Restart. Insightful experiments with a real user study show significant improvements in movie and book recommendations over item-level feedback.

Event-based online social platforms, such as Meetup and Plancast, have experienced increased popularity and rapid growth in recent years. In EBSN setup, selecting suitable venues for hosting events, which can attract a great turnout, is a key challenge. In this paper, we present a deep learning based venue recommendation system DeepVenue which provides context driven venue recommendations for the Meetup event-hosts to host their events. The crux of the proposed model relies on the notion of similarity between multiple Meetup entities such as events, venues, groups, etc. We develop deep learning techniques to compute a compact descriptor for each entity, such that two entities (say, venues) can be compared numerically. Notably, to mitigate the scarcity of venue related information in Meetup, we leverage on the cross domain knowledge transfer from popular LBSN service Yelp to extract rich venue related content. For hosting an event, the proposed DeepVenue model computes a success score for each candidate venue and ranks those venues according to the scores and finally recommend the top k venues. Our rigorous evaluation on the Meetup data collected for the city of Chicago shows that DeepVenue significantly outperforms the baselines algorithms. Precisely, for 84 percent of events, the correct hosting venue appears in the top 5 of the DeepVenue recommended list.

Direct answering of questions that involve multiple entities and relations is a challenge for text-based QA. This problem is most pronounced when answers can be found only by joining evidence from multiple documents. Curated knowledge graphs (KGs) may yield good answers, but are limited by their inherent incompleteness and potential staleness. This paper presents QUEST, a method that can answer complex questions directly from textual sources on-the-fly, by computing similarity joins over partial results from different documents. Our method is completely unsupervised, avoiding training-data bottlenecks and being able to cope with rapidly evolving ad hoc topics and formulation style in user questions. QUEST builds a noisy quasi KG with node and edge weights, consisting of dynamically retrieved entity names and relational phrases. It augments this graph with types and semantic alignments, and computes the best answers by an algorithm for Group Steiner Trees. We evaluate QUEST on benchmarks of complex questions, and show that it substantially outperforms state-of-the-art baselines.

Community detection in single layer, isolated networks has been extensively studied in the past decade. However, many real-world systems can be naturally conceptualized as multilayer networks which embed multiple types of nodes and relations. In this paper, we propose algorithm for detecting communities in multilayer networks. The crux of the algorithm is based on the multilayer modularity index Q_M, developed in this paper. The proposed algorithm is parameter-free, scalable and adaptable to complex network structures. More importantly, it can simultaneously detect communities consisting of only single type, as well as multiple types of nodes (and edges). We develop a methodology to create synthetic networks with benchmark multilayer communities. We evaluate the performance of the proposed community detection algorithm both in the controlled environment (with synthetic benchmark communities) and on the empirical datasets (Yelp and Meetup datasets); in both cases, the proposed algorithm outperforms the competing state-of-the-art algorithms.

Success of Meetup groups is of utmost importance for the members who organize them. Given a wide variety of such groups, a single metric may not be indicative of success for different groups; rather, success measure should be specific to the interest of a group. In this paper, accounting for the group diversity, we systematically define Meetup group success metrics and use them to generate labels for our machine learnt models. We crawl the Meetup dataset for three US cities namely New York, Chicago and San Francisco over a period of 8 months. The data study reveals the key players (such as core members, new members etc.) behind the success of the Meetup groups. This study leverages semantic, syntactic, temporal and location based features to discriminate between successful and unsuccessful groups. Finally, we present a model to predict success of the Meetup groups with high accuracy (0.81 with AUC = 0.86). Our approach generalizes well across groups, categories and cities. Additionally, the model performs reasonably well for new groups with little history (cold start problem), exhibiting high accuracy for the cross city validation.

In this paper, we investigate the role of mentions on tweet propagation. We propose a novel tweet propagation model SIR_MF based on a multiplex network framework, that allows to analyze the effects of mentioning on final retweet count. The basic bricks of this model are supported by a comprehensive study of multiple real datasets and simulations of the model show a nice agreement with the empirically observed tweet popularity. Studies and experiments also reveal that follower count, retweet rate & profile similarity are important factors in gaining tweet popularity and allow to better understand the impact of the mention strategies on the retweet count. Interestingly, we analytically identify a critical retweet rate regulating the role of mention on the tweet popularity. Finally, our data driven simulation demonstrates that the proposed mention recommendation heuristic "Easy-Mention" outperforms the benchmark "Whom-To-Mention" algorithm.