Expression.- Spectral Clustering Gene Ontology Terms to Group Genes by Function.- Dynamic De-Novo Prediction of microRNAs Associated with Cell Conditions: A Search Pruned by Expression.- Clustering Gene Expression Series with Prior Knowledge.- A Linear Time Biclustering Algorithm for Time Series Gene Expression Data.- Time-Window Analysis of Developmental Gene Expression Data with Multiple Genetic Backgrounds.- Phylogeny.- A Lookahead Branch-and-Bound Algorithm for the Maximum Quartet Consistency Problem.- Computing the Quartet Distance Between Trees of Arbitrary Degree.- Using Semi-definite Programming to Enhance Supertree Resolvability.- An Efficient Reduction from Constrained to Unconstrained Maximum Agreement Subtree.- Pattern Identification in Biogeography.- On the Complexity of Several Haplotyping Problems.- A Hidden Markov Technique for Haplotype Reconstruction.- Algorithms for Imperfect Phylogeny Haplotyping (IPPH) with a Single Homoplasy or Recombination Event.- Networks.- A Faster Algorithm for Detecting Network Motifs.- Reaction Motifs in Metabolic Networks.- Reconstructing Metabolic Networks Using Interval Analysis.- Genome Rearrangements.- A 1.375-Approximation Algorithm for Sorting by Transpositions.- A New Tight Upper Bound on the Transposition Distance.- Perfect Sorting by Reversals Is Not Always Difficult.- Minimum Recombination Histories by Branch and Bound.- Sequences.- A Unifying Framework for Seed Sensitivity and Its Application to Subset Seeds.- Generalized Planted (l,d)-Motif Problem with Negative Set.- Alignment of Tandem Repeats with Excision, Duplication, Substitution and Indels (EDSI).- The Peres-Shields Order Estimator for Fixed and Variable Length Markov Models with Applications to DNA Sequence Similarity.- Multiple Structural RNA Alignment with Lagrangian Relaxation.- Faster Algorithms for Optimal Multiple Sequence Alignment Based on Pairwise Comparisons.- Ortholog Clustering on a Multipartite Graph.- Linear Time Algorithm for Parsing RNA Secondary Structure.- A Compressed Format for Collections of Phylogenetic Trees and Improved Consensus Performance.- Structure.- Optimal Protein Threading by Cost-Splitting.- Efficient Parameterized Algorithm for Biopolymer Structure-Sequence Alignment.- Rotamer-Pair Energy Calculations Using a Trie Data Structure.- Improved Maintenance of Molecular Surfaces Using Dynamic Graph Connectivity.- The Main Structural Regularities of the Sandwich Proteins.- Discovery of Protein Substructures in EM Maps.

Algorithms in Bioinformatics: 5th International Workshop, WABI 2005, Mallorca, Spain, October 3-6, 2005, Proceedings (Lecture Notes in Computer Science / Lecture Notes in Bioinformatics)

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications. In this survey, we first describe the problem of learning with label noise from a supervised learning perspective. Next, we provide a comprehensive review of 46 state-of-the-art robust training methods, all of which are categorized into seven groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority. Subsequently, we summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics. Finally, we present several promising research directions that can serve as a guideline for future studies.

Learning from Noisy Labels with Deep Neural Networks: A Survey

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

LNBIP reports state-of-the-art results in areas related to business information systems and industrial application software development – timely, at a high level, and in both printed and electronic form.  The type of material published includes  • Proceedings (published in time for the respective event) • Postproceedings (consisting of thoroughly revised and/or extended final papers) • Other edited monographs (such as, for example, project reports or invited volumes) • Tutorials (coherently integrated collections of lectures given at advanced courses, seminars, schools, etc.) • Award-winning or exceptional theses LNBIP is abstracted/indexed in DBLP, EI and Scopus. LNBIP volumes are also submitted for the inclusion in ISI Proceedings.

Lecture notes in business information processing

Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the ranking problem, as it is not obvious how to learn from queries and documents when no supervised signal is available. Hence, in this paper, we propose to train a neural ranking model using weak supervision, where labels are obtained automatically without human annotators or any external resources (e.g., click data). To this aim, we use the output of an unsupervised ranking model, such as BM25, as a weak supervision signal. We further train a set of simple yet effective ranking models based on feed-forward neural networks. We study their effectiveness under various learning scenarios (point-wise and pair-wise models) and using different input representations (i.e., from encoding query-document pairs into dense/sparse vectors to using word embedding representation). We train our networks using tens of millions of training instances and evaluate it on two standard collections: a homogeneous news collection (Robust) and a heterogeneous large-scale web collection (ClueWeb). Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections. Our findings also suggest that supervised neural ranking models can greatly benefit from pre-training on large amounts of weakly labeled data that can be easily obtained from unsupervised IR models.

/pdf/neural-ranking-models-with-weak-supervision-39b2sa0fqc.pdf

Neural Ranking Models with Weak Supervision

A recent “third wave” of neural network (NN) approaches now delivers state-of-the-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, work in this area is often referred to as deep learning. Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created. In this paper, we survey the current landscape of Neural IR research, paying special attention to the use of learned distributed representations of textual units. We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research.

/pdf/neural-information-retrieval-at-the-end-of-the-early-years-144j0hldyz.pdf

Neural information retrieval: at the end of the early years

As the result of increasing population and growing technological activities, nonrenewable energy sources, which are the main energy providers, are diminishing day by day. Due to this factor, efforts on efficient utilization of renewable energy sources have increased all over the world. Wind is one of the most significant alternative energy resources. However, in comparison with other renewable energy sources, it is so variable that there is a need for estimating and planning of wind power generation. In this paper, a new statistical short-term (up to 48 h) wind power forecast model, namely statistical hybrid wind power forecast technique (SHWIP), is presented. In the proposed model, weather events are clustered with respect to the most important weather forecast parameters. It also combines the power forecasts obtained from three different numerical weather prediction (NWP) sources and produces a hybridized final forecast. The proposed model has been in operation at the Wind Power Monitoring and Forecast System for Turkey (RITM), and the results of the new model are compared with well-known statistical models and physical models in the literature. The most important characteristics of the proposed model is the need for a lesser amount of historical data while constructing the mathematical model compared with the other statistical models such as artificial neural networks (ANN) and support vector machine (SVM). To produce a reliable forecast, ANN and SVM need at least 1 year of historical data; on the other hand, the proposed SHWIP method’s results are applicable even under 1 month of training data, and this is an important feature for the forecast of the newly established wind power plants (WPPs).

A Novel Wind Power Forecast Model: Statistical Hybrid Wind Power Forecast Technique (SHWIP)

High utility sequential pattern mining has been considered as an important research problem and a number of relevant algorithms have been proposed for this topic. The main challenge of high utility sequential pattern mining is that, the search space is large and the efficiency of the solutions is directly affected by the degree at which they can eliminate the candidate patterns. Therefore, the efficiency of any high utility sequential pattern mining solution depends on its ability to reduce this big search space, and as a result, lower the computational complexity of calculating the utilities of the candidate patterns. In this paper, we propose efficient data structures and pruning technique which is based on Cumulated Rest of Match (CRoM) based upper bound. CRoM, by defining a tighter upper bound on the utility of the candidates, allows more conservative pruning before candidate pattern generation in comparison to the existing techniques. In addition, we have developed an efficient algorithm, High Utility Sequential Pattern Extraction (HuspExt), which calculates the utilities of the child patterns based on that of the parents’. Substantial experiments on both synthetic and real datasets from different domains show that, the proposed solution efficiently discovers high utility sequential patterns from large scale datasets with different data characteristics, under low utility thresholds.

CRoM and HuspExt: Improving Efficiency of High Utility Sequential Pattern Extraction

The location-based social networks (LBSN) facilitate users to check-in their current location and share it with other users. The accumulated check-in data can be employed for the benefit of users by providing personalized recommendations. In this paper, we propose a random walk based context-aware friend recommendation algorithm (RWCFR). RWCFR considers the current context (i.e. current social relations, personal preferences and current location) of the user to provide personalized recommendations. Our LBSN model is an undirected unweighted graph model that represents users, locations, and their relationships. We build a graph according to the current context of the user depending on this LBSN model. In order to rank the recommendation scores of the users for friend recommendation, a random walk with restart approach is employed. We compare RWCFR with popularity-based, friend-based and expert-based baseline approaches. According to the results, our friend recommendation algorithm outperforms these approaches in all the tests.

Context-Aware Friend Recommendation for Location Based Social Networks using Random Walk

The location-based social networks (LBSN) enable users to check in their current location and share it with other users. The accumulated check-in data can be employed for the benefit of users by providing personalized recommendations. In this paper, we propose a context-aware location recommendation system for LBSNs using a random walk approach. Our proposed approach considers the current context (i.e., current social relations, personal preferences and current location) of the user to provide personalized recommendations. We build a graph model of LBSNs for performing a random walk approach with restart. Random walk is performed to calculate the recommendation probabilities of the nodes. A list of locations are recommended to users after ordering the nodes according to the estimated probabilities. We compare our algorithm, CLoRW, with popularity-based, friend-based and expert-based baselines, user-based collaborative filtering approach and a similar work in the literature. According to experimental results, our algorithm outperforms these approaches in all of the test cases.

Pinar Karagoz

Papers

Neural information retrieval: at the end of the early years

A Novel Wind Power Forecast Model: Statistical Hybrid Wind Power Forecast Technique (SHWIP)

CRoM and HuspExt: Improving Efficiency of High Utility Sequential Pattern Extraction

Context-Aware Friend Recommendation for Location Based Social Networks using Random Walk

Context-aware location recommendation by using a random walk-based approach