Step by step guide to writing a thesis statement, how to write more formally. General writing ielts essay write dissertation research methods free download essay on corruption Harvard mba essay help get homework help. Submit resume and salary history. Custom definition essay ghostwriters site au papers Torrent repository academic. Popular phd dissertation hypothesis ideas write custom creative essay on founding fathers enterprise research paper for cheap repository papers Torrent academic, dare to dream essay esl admission essay ghostwriter sites usa , resume format for professionals doc, the girls in their summer dresses analytical essay.

Essay about problems in life nyu essay questions , belief essay topics, dissertation apa citation cheap movie review ghostwriter services for college. Pay to get professional best essay on lincoln, student finance print cover letter error. Essay on power of endurance cheap movie review editor for hire uk , professional article proofreading for hire online masters thesis dissertation francis bacon essays of beauty. Popular research proposal writer services for school. Sample business plan photography harvard mba essay help custom best essay writers site for phd. Sample cover letter for uk tourist visa application best graphic design resume examples, research papers on human resource management. Paano gumawa ng isang magandang essay. Thesis statements for a research paper population ecology essay questions?

Literature review functional electrical stimulation parental involvement essay, esl assignment ghostwriters sites ca. There are two main modules: text encoding and constrained GCN. The first module tries to develop a text encoding technique to encode the content information of papers and repositories into vectors as inputs of the constrained GCN model. The second module implements the GCN model with an added constraint. The constraint specifies that repositories explicitly mentioned in paper descriptions must be mapped to the same place as the referring paper, thereby linking the mappings of repositories and papers into a single consistent space.

We detail these two modules in the following. Text encoding. In general, the descriptions of repositories are limited and simple, so it is difficult to learn the overall features of repositories from them. Hence, we add the tags from repositories to enrich the descriptions, because tags often extract some key information about the topics of the repositories on GitHub. Therefore, we design the text encoding module to encode the features of both tags and descriptions. As illustrated in Fig. We first use Step 1 and Step 2 to encode the descriptions of a repository as shown in Fig.

The word vector comes from the pre-trained embeddings of Wiki words offered by the GloVe algorithm penningtonglove. The length of each description is fixed to n padded or cropped where necessary. So a description can be defined by. where b is a bias parameter and f. is a non-linear activation function such as ReLU. After obtaining the feature map, a max-over-time pooling operation is adopted to get the maximum value, max { c } , of each output feature map as illustrated in Step 2. Next, we implement Step 3 to encode tags. Since there is no sequence for tags, we leverage fully connected layers to learn their features.

For each tag, we first use the fastText trick joulinbag to get its word representation via merging the embeddings of each word. Here, fastText is a simple text encoding technique where word embeddings are averaged into a single vector. We then apply fully connected layers to produce the new features whose dimensions are aligned with the number of feature maps for description encoding. After that, feature fusion is adopted in Step 4 to add the new features of tags generated in Step 3 to the produced features in Step 2. Finally, the new features, v j , integrated with description encoding and tag encoding are input of the constrained GCN model.

In order to improve the stability of model training, we adopt batch normalization to normalize the new features. Similarly, for abstract encoding of a paper, we can propose the same methodology to learn the new features as the description encoding of a repository in Step 1 and Step 2. For brevity, we will not describe it in detail. Constrained GCN model. Since papers and repositories are in two different platforms, the generated embeddings by the traditional GCN are not in the same space. Thus, we propose a constrained GCN model to constrain the embeddings to the same space. Specifically, it leverages the general GCN as the forward propagation model in Equation 1 and minimizes the distance between the embeddings of some bridge papers and their original repositories as a constraint.

We use the cosine similarity to measure the distance. In order to compute the cosine similarity distance for the embeddings, we normalize their embeddings as. where ϵ is a small error term, such as 0. In this paper, we adopt weighted approximate-rank pairwise WARP loss westonwsabie to train the paper2repo model in order to recommend the target repositories to a query paper at the top of the ranked candidates. Let L be the WARP loss for the labeled pairs of papers and repositories during training, and m be the number of pairs for bridge papers and their original repositories in the training data.

Then, the constrained GCN model is defined as:. In the above 6 , the WARP loss function. In addition, L. First, L. in 7 is a transformation function which transforms the rank into a loss, defined as. where K denotes the position of a positive example in the ranked list. where I. is the indicator function that outputs 1 or 0. After defining the WARP loss, the next step is to solve the above non-linear optimization model in 6. One possible solution is to transform it into a dual problem. Based on the method of Lagrange multipliers, we can rewrite the above constrained model 6 as:.

It is very hard to obtain a closed-form solution that minimizes the objective function 10 due to the nonlinear nature of the optimization problem. Instead, we feed this objective function as a new loss function to the neural network. Convergence of training of this neural network to a solution that meets both the original loss function, L left term in objective function 10 , and the joint embedding constraint right term in objective function 10 , requires that the two terms have comparable weights. Otherwise, learning gradients will favor optimizing the larger term and ignore the smaller.

Unfortunately, the loss function L dynamically drops during training, making it difficult to choose the hyper-parameter, λ , to create gradients that properly trade off the loss function, L , and the constraint error. To address this issue, we replace λ in the second term with the varying WARP loss, L , and normalize the constraint error instead of using the total error. Accordingly, our model can be formulated as:. where C e is the average constraint error, defined as:. Thus, each term in the summation above ranges between 0 and 2. The entire summation ranges between 0 and 2 m , and the normalization leads to a value of C e between 0 and 1.

Using the mean constraint error, C e , helps keep the scale of the two terms in the objective function 11 comparable. While hypothetically, we can even remove the constant, 1, from objective function 11 , we find that keeping it improves numeric stability and convergence. In the new formulation, we no longer need to dynamically adjust the hyper-parameter, λ , for model training. The constrained optimization problem in 6 can be solved by minimizing the new loss function 11 by feeding it to the graph neural network. We summarize the main notations used in our model in Table 1. The output of our trained network is the ranked inner products of the embeddings for pairs of papers and repositories.

The closer the embeddings of a paper and a repository, the higher their inner product, and the higher the ranking. Given that output, one can identify the top ranked recommended repositories for a given paper or the top ranked papers for a given repository. Training computes the weights and biases of each convolutional neural network layer, the weights and biases of each fully connected layer for tag encoding , and the weights and biases of filters for the convolution operation. Besides, we need to tune the number of filters used for text encoding, the filter window h , the number of fully connected layers for tag encoding of repositories, the number of hidden layers of neural networks, and the dimension of output embeddings of each node as well as the margin hyper-parameter for WARP loss.

We set the output dimension of representations embeddings of each paper and repository equal in order to compute their similarity scores. We then select positive and negative samples as follows:. Positive samples: We use the bridge papers and the corresponding repositories as labeled training data. Let p i be the i -th paper and r j be its highly related repositories. Such pairs, p i , r j , constitute positive samples. We further hypothesize that if users, who star repository A, also star repository B more often than C, then on average B is more related than C to repository A. Thus, besides bridge repositories, we collect the top T related repositories, ranked by the frequency they are starred by users who star the original bridge repository. In order to get more training data, we also sample some one-hop neighbors of bridge papers combined with the corresponding bridge repositories to be positive examples at most T.

We can think of this method as a form of distant supervision; an imperfect heuristic to label more samples than what can be inferred from explicit bridge references. It is important to note that we. Negative samples: We also introduce negative examples, referring to repositories that are not highly related to a query paper. In this work, we randomly sample n k negative examples of repositories across the entire graph to train the model. We expect the similarity scores of positive examples to be larger than those of negative examples. We briefly summarize the proposed constrained GCN algorithm in Algorithm 1. In this algorithm, the first l layers learn the hidden vectors embeddings of each paper and repository using the GCN algorithm in 1. Then we use the normalized embeddings of paper p i , and repository r j to compute their similarity scores.

Additionally, we try to minimize the distance between the embeddings of bridge papers and their original repositories as an added constraint. We carry out experiments to evaluate the performance of the proposed paper2repo on the real-world data sets collected from GitHub and Microsoft Academic. Further, we show that the proposed model performs well on larger data sets without any hyper-parameter tuning. In addition, we conduct ablation experiments to explore how design choices impact performance. Finally, we conduct a case study to evaluate the effectiveness of the proposed method. We collected a repository data set and a research paper data set from GitHub and Microsoft Academic, respectively. Microsoft Academic provides an API for users to query the detailed entities of academic papers, such as paper title, abstract, and venue names.

For a proof of concept, we query the top 20 venue names and 8 journals of computer science, such as KDD, WWW, ACL, ICML, NIPS, CVPR and TKDE, to retrieve the entities of 59 , raw papers from year to After that, we query for the titles of these papers to collect some original open source repositories through the GitHub API. We obtain about 2 , original repositories corresponding to the named papers. We define bridge papers as those for which we found a matching repository which we call the bridge repository. In addition, we collect about 8 , popular repositories from users who star the bridge repositories. After data cleaning and preprocessing, we have 32 , research papers and 7 , repositories, including 2 , bridge repositories. In our experiments, we evaluate the performance of the proposed model on both small and full data sets as illustrated in Table 2.

Testing and ground truth estimation. It remains to describe how we partition data into the training set and test set. We already described how positive and negative training pairs were selected. It is tempting to try and choose test papers and repositories at random. However, due to the large number of papers and repositories available on the respective platforms, this random sampling leads to a predominance of unrelated pairs, unless the test set is very large which would be very expensive to label.

In other words, the test set has to include related pairs. Hence, we first selected bridge papers and their one-hop neighbors not present in the training set. We then included their repositories as well as the two hop neighborhood of those repositories according to the context graph. Thus, for each paper in the test set, we included some repositories that are likely related to different degrees, and hundreds of repositories that are likely not related i. This allowed for a much richer diversity in the test set and Mechanical Turk outputs. It is important to underscore that the criteria above were used merely for paper and repository selection for inclusion in the test set. The labeling of the degree of match for pairs returned by the recommender was done strictly by human graders and not by machine heuristics.

Baseline methods. We compare the proposed paper2repo with the algorithms below:. NSCR wangitem : This is a cross-domain recommendation framework that combines deep fully connected layers with graph Laplacian to recommend items from information domain to social domains. KGCN wangknowledge : This method leverages knowledge graph and graph convolutional neural networks to recommend interested items to users. CDL wangcollaborative : This is a hybrid recommendation algorithm, which jointly performs deep representation learning for the content information and collaborative filtering for the ratings matrix.

NCF heneural : This is a neural collaborative filtering model for recommendation, which combines the matrix factorization MF and MLP to learn the user-item relationship. LINE tangline : This is a graph embedding algorithm that uses BFS to learn the embedding of nodes in the graph with unsupervised learning. In order to better perform LINE, we construct the entire graph of papers and repositories via the bridge papers and their original repositories. MF vandeep : This method is widely used for traditional recommender systems due to its good performance for dense data. BPR rendlebpr : This is an optimized MF model with Bayesian analysis for implicit recommendation.

It is a supervised model and we use the same method as MF to do experiments. Evaluation measures. In order to evaluate the performance of the proposed paper2repo recommender system, this paper adopts three commonly used information retrieval measures: HR K hit ratio , MAP K mean average precision , MRR K mean reciprocal rank. In general, HR is used to measure the accuracy about the number of correct repositories recommended by the. Model architecture and parameters. In order to compare the performance of our proposed paper2repo to the other recommender algorithms, we tune the hyper-parameters during model training. After extensive experiments not shown , we obtain the best parameters for our model below: we set the number of layers to 2 for the graph convolutional neural networks and the size of each layer to The number of fully connected layers is 2 for tags encoding of repositories.

The length of each abstract from papers, and description of repositories is fixed to and 50, respectively. For paper abstract encoding, the filter window h is 2, 3, 5, 7 with 64 feature maps each. For repository descriptions encoding, its filter windows h is 2, 4 with 64 and 32 feature maps, respectively. The pre-trained embeddings of words produced by GloVe are used with size of We set the learning rate to 0. For training, we set the number of positive repositories, T , to 6 given a paper. In addition, we randomly sample 44 negative samples to train the model.

We set the margin hyper-parameter, Δ , to 0. Our evaluation results are obtained by averaging 3 runs per point. To understand dependence on scale, we start with a subset of 11 , papers and 7 , repositories, including 1 , pairs of bridge papers and original repositories, to conduct experiments later we shall use the full data set. We compare the performance of the proposed paper2repo with the competing methods. We can observe that the proposed paper2repo outperforms the other recommendation algorithms for all the three metrics. This is because our paper2repo encodes both the contents and graph structures of papers and repositories to learn their embeddings. In addition, paper2repo performs better than the cross-domain NCSR algorithm for two reasons. First of all, NCSR leverages spectral embeddings method without using node features in social domain, while our model encodes both content information and graph structures.

Secondly, the items in our data sets have more attributes keywords and tags than that 20 attributes in the NCSR paper, making it hard to train the NCSR model. In Fig. This reason is that more positive repositories are recommended but not at the top of ranking list, leading to lower MAP. Moreover, we can observe that CDL and NCF do not perform well in our case. The main reason is that the number of positive examples for model training is very small such that they suffer from data sparsity as the traditional MF. Besides, KGCN does not work very well because it only adopts one hot embedding without taking node features into account in the paper domain.

We conduct another experiment to evaluate the performance of the paper2repo on larger data sets. We do not otherwise perform any data-set-specific tuning. We change the number of papers from 11 , to 32 , , and the number of pairs of bridge papers and their original repositories from 1 , to 2 , From this figure, it can be observed that the proposed paper2repo performs better on larger data sets than that on small data sets in terms of MAP and MRR, and their hit ratios are comparable. The is because our model can learn more information from different nodes in a large-scale graph.

Effect of Pre-trained Embeddings. We first explore how the settings of pre-trained embeddings impact the performance of the proposed paper2repo. We compare three different cases: i fixed pre-trained embeddings; ii pre-trained embeddings are used as initialization not fixed ; iii fixed and not fixed embeddings are concatenated together. We can see that when the pre-trained embeddings are fixed, it performs better than the other two cases. The main reason is that the pre-trained embeddings are produced from the large Wikipedia corpus by GloVe.

The performance of concatenated embeddings seems not very good, because it is more difficult to train the model with more complicated networks. Effect of top T positive repositories. Next, we explore how the number of positive repositories in training, T , influences the performance of paper2repo. In our experiment, the number of positive repositories, T , varies from 3 to 7 with step 1. From Table 4 , it can be seen that the performance of paper2repo gradually boosts as T increases from 3 to 6. Thus, we can find that paper2repo has a better performance when the number of positive repositories in training is large in some degree.

Effect of the Margin Hyper-parameter. We also study the impact of the margin hyper-parameter on the performance of the paper2repo. We change the margin parameter, Δ , from 0. We can observe that the performance of paper2repo gradually increases as Δ rises from 0. The main reason is that as margin Δ is too small, it is hard to separate the positive and negative examples. At the same time, a larger Δ may result in higher loss during training. Effect of Number of Bridge Papers. Finally, we explore how the number of bridge papers and repositories affect the recommendation performance of paper2repo.

Table 6 illustrates the comparison results under different ratios of 1 , bridge papers in the small data set. We can observe from it that the evaluation metrics , HR, MAP and HRR, gradually rise as the number of bridge papers increases. This is because more bridge papers and repositories can make the embeddings of the similar nodes closer to each other in the graph. We further discuss the advantages and disadvantages of pape2repo. According to our experiments, we discover that the recommended repositories are relevant to a query paper when there exists substantial user co-starring between bridge repositories and other repositories or when there are multiple overlapped tags between them.

The main reason is that two repositories starred by many of the same users or that have multiple overlapped keywords are very likely to involve similar research topics. However, when only few users star both repositories, the recommendation performance is not very good. For example, when two repositories are only starred by a couple of users together, it is hard to judge whether these two repositories are similar or not. As a result, the recommended repositories seem not to be very relevant to the query papers. The need to find a sufficient number of bridge repositories is another limitation.

Cold start is one of the most important research topics in recommender systems. As we know, when users release new source code, their repositories have very little user starring in the beginning. Thus, in practice, cold start is an issue similar to lack of sufficient co-starring, discussed above. Our pape2repo is able to partially deal with cold start because, as mentioned in Section 2. Even if a repository has very few stars, we can still use its tags to construct the repository graph. Therefore, we can still recommend some repositories to the query papers, although the qualify of recommendation will be impacted.

The accuracy of our evaluation results is impacted by the accuracy of estimating ground truth. Due to budget constraints, we used three Mechanical Turk graders per item, when they coincided. Grading reliability can be improved by increasing the graders and performing grader training. Other limitations include the general applicability of repository recommendations. While software libraries are becoming an increasingly important research enabler, some fields including theory are less likely to benefit from this system. The system is also less relevant to research enabled by artifacts not in the public domain. One may also argue that authors will tend to cite relevant repositories as a best practice.

This is true, but our recommender system can also uncover subsequently created repositories that impact a given paper, such as novel implementations of relevant libraries, or algorithm implementations on new hardware platforms and accelerators. This is the same reason why one might not exclusively rely on citations in a paper to find other relevant papers, especially if the paper in question is a few years old. This section reviews related work on recommender systems that use deep learning and graph neural networks, especially for cross-domain recommendations.

In order to deal with data sparsity and cold start issues in recommender systems, recent research proposed cross-domain recommendations elkahkymulti ; wangitem ; jiangsocial ; jianglittle to enrich user preferences with auxiliary information from other platforms. Cross-domain recommendations get rich information on items that users prefer buying based on their history on multiple platforms. For example, some users like to purchase furniture on Walmart and buy clothes on Amazon. So we can recommend furniture to the users on Amazon next time, which can improve the diversity of recommendations.

Motivated by this observation, a multi-view deep learning model was proposed by Elkahky et al.

Academic Torrents [1] [2] [3] [4] [5] [6] is a website which enables the sharing of research data using the BitTorrent protocol. The site was founded in November , and is a project of the Institute for Reproducible Research a c 3 U. non-profit corporation. The developing Human Connectome Project which is related to the Human Connectome Project uses the platform. The researchers opted to go for the Academic Torrents tracker, which specializes in sharing research data" [11]. This was done so to allow the community to work with the entire database programmatically instead of using their API. We hope this saves the research community valuable time during this crisis. From Wikipedia, the free encyclopedia. File-sharing website. The logo is a DFA representing multiple phrases describing the platform.

BitTorrent tracker Digital library. Archived from the original on 26 July Retrieved 6 May Torrent Freak. Archived from the original on 28 May Archived from the original on 8 June Archived from the original on 22 September Proceedings of the Annual Conference on Extreme Science and Engineering Discovery Environment. doi : S2CID Neural Information Processing Systems Challenges in Machine Learning CiML Workshop. arXiv : Retrieved 4 May United States IRS. Library Journal. Archived from the original on 7 May Vice News. Archived from the original on 25 September Archived from the original on 5 January Archived from the original on Retrieved Categories : BitTorrent websites Creative Commons-licensed works Open-access archives Scholarly communication Open science Collaborative software Open data Academic publishing Data publishing Institutional repository software c 3 organizations Access to Knowledge movement American digital libraries Foundations based in the United States Metascience-related organizations.

Hidden categories: Articles with short description Short description matches Wikidata. Navigation menu Personal tools Not logged in Talk Contributions Create account Log in. Namespaces Article Talk. Views Read Edit View history. Main page Contents Current events Random article About Wikipedia Contact us Donate. Help Learn to edit Community portal Recent changes Upload file. What links here Related changes Upload file Special pages Permanent link Page information Cite this page Wikidata item. Download as PDF Printable version. Add links. Joseph Paul Cohen Henry Z Lo.

Finally, we conclude the paper in Section 6. The money will be transferred to your writer in case you approve the paper. Instead, we feed this objective function as a new loss function to the neural network. Availability Available worldwide. In order to compute the cosine similarity distance for the embeddings, we normalize their embeddings as p i and r j , respectively. It is important because we want to be sure that our potential writers have sufficient background.

Categories:

• Custom Essays
• Essay Online
• Online Essays
• Essay Website
• Essay Experts