This paper explores online learning approaches for detecting malicious Web sites (those involved in criminal scams) using lexical and host-based features of the associated URLs. We show that this application is particularly appropriate for online algorithms as the size of the training data is larger than can be efficiently processed in batch and because the distribution of features that typify malicious URLs is changing continuously. Using a real-time system we developed for gathering URL features, combined with a real-time source of labeled URLs from a large Web mail provider, we demonstrate that recentlydeveloped online algorithms can be as accurate as batch techniques, achieving classification accuracies up to 99 % over a balanced data set. 1.

Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the structured perceptron can be costly to train as training complexity is proportional to inference, which is frequently non-linear in example sequence length. In this paper we investigate distributed training strategies for the structured perceptron as a means to reduce training times when computing clusters are available. We look at two strategies and provide convergence bounds for a particular mode of distributed structured perceptron training based on iterative parameter mixing (or averaging). We present experiments on two structured prediction problems – namedentity recognition and dependency parsing – to highlight the efficiency of this method. 1

Incorporating features extracted from clickthrough data (called clickthrough features) has been demonstrated to significantly improve the performance of ranking models for Web search applications. Such benefits, however, are severely limited by the data sparseness problem, i.e., many queries and documents have no or very few clicks. The ranker thus cannot rely strongly on clickthrough features for document ranking. This paper presents two smoothing methods to expand clickthrough data: query clustering via Random Walk on click graphs and a discounting method inspired by the Good-Turing estimator. Both methods are evaluated on real-world data in three Web search domains. Experimental results show that the ranking models trained on smoothed clickthrough features consistently outperform those trained on unsmoothed features. This study demonstrates both the importance and the benefits of dealing with the sparseness problem in clickthrough data.

We present AROW, a new online learning algorithm that combines several useful properties: large margin training, confidence weighting, and the capacity to handle non-separable data. AROW performs adaptive regularization of the prediction function upon seeing each new instance, allowing it to perform especially well in the presence of label noise. We derive a mistake bound, similar in form to the second order perceptron bound, that does not assume separability. We also relate our algorithm to recent confidence-weighted online learning techniques and show empirically that AROW achieves state-of-the-art performance and notable robustness in the case of non-separable data. 1

Confidence-weighted (CW) learning [6], an online learning method for linear classifiers, maintains a Gaussian distributions over weight vectors, with a covariance matrix that represents uncertainty about weights and correlations. Confidence constraints ensure that a weight vector drawn from the hypothesis distribution correctly classifies examples with a specified probability. Within this framework, we derive a new convex form of the constraint and analyze it in the mistake bound model. Empirical evaluation with both synthetic and text data shows our version of CW learning achieves lower cumulative and out-of-sample errors than commonly used first-order and second-order online methods. 1

Stories of people's everyday experiences have long been the focus of psychology and sociology research, and are increasingly being used in innovative knowledge-based technologies. However, continued research in this area is hindered by the lack of standard corpora of sufficient size and by the costs of creating one from scratch. In this paper, we describe our efforts to develop a standard corpus for researchers in this area by identifying personal stories in the tens of millions of blog posts in the ICWSM 2009 Spinn3r Dataset. Our approach was to employ statistical text classification technology on the content of blog entries, which required the creation of a sufficiently large set of annotated training examples. We describe the development and evaluation of this classification technology and how it was applied to the dataset in order to identify nearly a million personal stories. Weblog Stories as Data In a telephone survey of a nationally representative sample of bloggers conducted by the Pew Internet & American Life Project (Lenhart & Fox, 2006), American bloggers most frequently cited “my life and experiences ” as a primary topic of their blog (37%). Nearly one million new blog posts are made each day on the web (Technorati.com, 2008), raising the possibilities for new quantitative approaches to the study and analysis of human life and experiences where weblog text is treated as data. In pursuing these new quantitative approaches, it is important to understand how the content that bloggers characterize as “my life and experiences ” relates to the text that they actually compose. One particularly interesting presentation of life experiences in weblogs is in the genre of the personal story, consisting of the non-fiction narratives and anecdotes that people tell about their lives. In our research we define personal stories as textual discourse that describes a specific series of causally related events in the past, spanning a period of time of minutes, hours, or days, where the

The recently introduced online confidence-weighted (CW) learning algorithm for binary classification performs well on many binary NLP tasks. However, for multi-class problems CW learning updates and inference cannot be computed analytically or solved as convex optimization problems as they are in the binary case. We derive learning algorithms for the multi-class CW setting and provide extensive evaluation using nine NLP datasets, including three derived from the recently released New York Times corpus. Our best algorithm outperforms state-of-the-art online and batch methods on eight of the nine tasks. We also show that the confidence information maintained during learning yields useful probabilistic information at test time. 1

Large templated factor graphs with complex structure that changes during inference have been shown to provide state-of-the-art experimental results on tasks such as identity uncertainty and information integration. However, learning parameters in these models is difficult because computing the gradients require expensive inference routines. In this paper we propose an online algorithm that instead learns preferences over hypotheses from the gradients between the atomic steps of inference. Although there are a combinatorial number of ranking constraints over the entire hypothesis space, a connection to the frameworks of sampled convex programs reveals a polynomial bound on the number of rankings that need to be satisfied in practice. We further apply ideas of passive aggressive algorithms to our update rules, enabling us to extend recent work in confidenceweighted classification to structured prediction problems. We compare our algorithm to structured perceptron, contrastive divergence, and persistent contrastive divergence, demonstrating substantial error reductions on two real-world problems (20 % over contrastive divergence).

Leading classification methods such as support vector machines (SVMs) and their counterparts achieve strong generalization performance by maximizing the margin of separation between data classes. While the maximum margin approach has achieved promising performance, this article identifies its sensitivity to affine transformations of the data and to directions with large data spread. Maximum margin solutions may be misled by the spread of data and preferentially separate classes along large spread directions. This article corrects these weaknesses by measuring margin not in the absolute sense but rather only relative to the spread of data in any projection direction. Maximum relative margin corresponds to a data-dependent regularization on the classification function while maximum absolute margin corresponds to an ℓ2 norm constraint on the classification function. Interestingly, the proposed improvements only require simple extensions to existing maximum margin formulations and preserve the computational efficiency of SVMs. Through the maximization of relative margin, surprising performance gains are achieved on real-world problems such as digit, image histogram, and text classification. In addition, risk bounds are derived for the new formulation based on Rademacher averages.

We develop a novel online learning algorithm for the group lasso in order to efficiently find the important explanatory factors in a grouped manner. Different from traditional batch-mode group lasso algorithms, which suffer from the inefficiency and poor scalability, our proposed algorithm performs in an online mode and scales well: at each iteration one can update the weight vector according to a closed-form solution based on the average of previous subgradients. Therefore, the proposed online algorithm can be very efficient and scalable. This is guaranteed by its low worst-case time complexity and memory cost both in the order of O(d), where d is the number of dimensions. Moreover, in order to achieve more sparsity in both the group level and the individual feature level, we successively extend our online system to efficiently solve a number of variants of sparse group lasso models. We also show that the online system is applicable to other group lasso models, such as the group lasso with overlap and graph lasso. Finally, we demonstrate the merits of our algorithm by experimenting with both synthetic and real-world datasets. 1.