Paper Group ANR 1717
Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification. Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing. Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation. Verification and Validation of Semantic Annotations. A difficulty ranking approa …
Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification
| Title | Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification |
| Authors | Kaisheng Gao, Jing Zhang, Cangqi Zhou |
| Abstract | The graph convolution network (GCN) is a widely-used facility to realize graph-based semi-supervised learning, which usually integrates node features and graph topologic information to build learning models. However, as for multi-label learning tasks, the supervision part of GCN simply minimizes the cross-entropy loss between the last layer outputs and the ground-truth label distribution, which tends to lose some useful information such as label correlations, so that prevents from obtaining high performance. In this paper, we pro-pose a novel GCN-based semi-supervised learning approach for multi-label classification, namely ML-GCN. ML-GCN first uses a GCN to embed the node features and graph topologic information. Then, it randomly generates a label matrix, where each row (i.e., label vector) represents a kind of labels. The dimension of the label vector is the same as that of the node vector before the last convolution operation of GCN. That is, all labels and nodes are embedded in a uniform vector space. Finally, during the ML-GCN model training, label vectors and node vectors are concatenated to serve as the inputs of the relaxed skip-gram model to detect the node-label correlation as well as the label-label correlation. Experimental results on several graph classification datasets show that the proposed ML-GCN outperforms four state-of-the-art methods. |
| Tasks | Graph Classification, Graph Embedding, Multi-Label Classification, Multi-Label Learning, Node Classification |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05743v1 |
| https://arxiv.org/pdf/1907.05743v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-graph-embedding-for-multi |
| Repo | |
| Framework | |
Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
| Title | Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing |
| Authors | Vedika Agarwal, Rakshith Shetty, Mario Fritz |
| Abstract | Despite significant success in Visual Question Answering (VQA), VQA models have been shown to be notoriously brittle to linguistic variations in the questions. Due to deficiencies in models and datasets, today’s models often rely on correlations rather than predictions that are causal w.r.t. data. In this paper, we propose a novel way to analyze and measure the robustness of the state of the art models w.r.t semantic visual variations as well as propose ways to make models more robust against spurious correlations. Our method performs automated semantic image manipulations and tests for consistency in model predictions to quantify the model robustness as well as generate synthetic data to counter these problems. We perform our analysis on three diverse, state of the art VQA models and diverse question types with a particular focus on challenging counting questions. In addition, we show that models can be made significantly more robust against inconsistent predictions using our edited data. Finally, we show that results also translate to real-world error cases of state of the art models, which results in improved overall performance |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07538v2 |
| https://arxiv.org/pdf/1912.07538v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-causal-vqa-revealing-and-reducing |
| Repo | |
| Framework | |
Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation
| Title | Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation |
| Authors | Shuo Zhang, Lei Xie |
| Abstract | Graph Neural Networks (GNNs) are powerful to learn the representation of graph-structured data. Most of the GNNs use the message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information of its neighbors. To achieve a better expressive capability of node influences, attention mechanism has grown to be popular to assign trainable weights to the nodes in aggregation. Though the attention-based GNNs have achieved remarkable results in various tasks, a clear understanding of their discriminative capacities is missing. In this work, we present a theoretical analysis of the representational properties of the GNN that adopts the attention mechanism as an aggregator. Our analysis determines all cases when those attention-based GNNs can always fail to distinguish certain distinct structures. Those cases appear due to the ignorance of cardinality information in attention-based aggregation. To improve the performance of attention-based GNNs, we propose cardinality preserved attention (CPA) models that can be applied to any kind of attention mechanisms. Our experiments on node and graph classification confirm our theoretical analysis and show the competitive performance of our CPA models. |
| Tasks | Graph Classification |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02204v3 |
| https://arxiv.org/pdf/1907.02204v3.pdf | |
| PWC | https://paperswithcode.com/paper/improving-attention-mechanism-in-graph-neural |
| Repo | |
| Framework | |
Verification and Validation of Semantic Annotations
| Title | Verification and Validation of Semantic Annotations |
| Authors | Oleksandra Panasiuk, Omar Holzknecht, Umutcan Şimşek, Elias Kärle, Dieter Fensel |
| Abstract | In this paper, we propose a framework to perform verification and validation of semantically annotated data. The annotations, extracted from websites, are verified against the schema.org vocabulary and Domain Specifications to ensure the syntactic correctness and completeness of the annotations. The Domain Specifications allow checking the compliance of annotations against corresponding domain-specific constraints. The validation mechanism will detect errors and inconsistencies between the content of the analyzed schema.org annotations and the content of the web pages where the annotations were found. |
| Tasks | |
| Published | 2019-04-02 |
| URL | https://arxiv.org/abs/1904.01353v2 |
| https://arxiv.org/pdf/1904.01353v2.pdf | |
| PWC | https://paperswithcode.com/paper/verification-and-validation-of-semantic |
| Repo | |
| Framework | |
A difficulty ranking approach to personalization in E-learning
| Title | A difficulty ranking approach to personalization in E-learning |
| Authors | Avi Segal, Kobi Gal, Guy Shani, Bracha Shapira |
| Abstract | The prevalence of e-learning systems and on-line courses has made educational material widely accessible to students of varying abilities and backgrounds. There is thus a growing need to accommodate for individual differences in e-learning systems. This paper presents an algorithm called EduRank for personalizing educational content to students that combines a collaborative filtering algorithm with voting methods. EduRank constructs a difficulty ranking for each student by aggregating the rankings of similar students using different aspects of their performance on common questions. These aspects include grades, number of retries, and time spent solving questions. It infers a difficulty ranking directly over the questions for each student, rather than ordering them according to the student’s predicted score. The EduRank algorithm was tested on two data sets containing thousands of students and a million records. It was able to outperform the state-of-the-art ranking approaches as well as a domain expert. EduRank was used by students in a classroom activity, where a prior model was incorporated to predict the difficulty rankings of students with no prior history in the system. It was shown to lead students to solve more difficult questions than an ordering by a domain expert, without reducing their performance. |
| Tasks | |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12047v1 |
| https://arxiv.org/pdf/1907.12047v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-difficulty-ranking-approach-to |
| Repo | |
| Framework | |
iPool – Information-based Pooling in Hierarchical Graph Neural Networks
| Title | iPool – Information-based Pooling in Hierarchical Graph Neural Networks |
| Authors | Xing Gao, Hongkai Xiong, Pascal Frossard |
| Abstract | With the advent of data science, the analysis of network or graph data has become a very timely research problem. A variety of recent works have been proposed to generalize neural networks to graphs, either from a spectral graph theory or a spatial perspective. The majority of these works however focus on adapting the convolution operator to graph representation. At the same time, the pooling operator also plays an important role in distilling multiscale and hierarchical representations but it has been mostly overlooked so far. In this paper, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs. With the argument that informative nodes dominantly characterize graph signals, we propose a criterion to evaluate the amount of information of each node given its neighbors, and theoretically demonstrate its relationship to neighborhood conditional entropy. This new criterion determines how nodes are selected and coarsened graphs are constructed in the pooling layer. The resulting hierarchical structure yields an effective isomorphism-invariant representation of networked data in arbitrary topologies. The proposed strategy is evaluated in terms of graph classification on a collection of public graph datasets, including bioinformatics and social networks, and achieves state-of-the-art performance on most of the datasets. |
| Tasks | Graph Classification |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00832v2 |
| https://arxiv.org/pdf/1907.00832v2.pdf | |
| PWC | https://paperswithcode.com/paper/ipool-information-based-pooling-in |
| Repo | |
| Framework | |
Speeding Up Iterative Closest Point Using Stochastic Gradient Descent
| Title | Speeding Up Iterative Closest Point Using Stochastic Gradient Descent |
| Authors | Fahira Afzal Maken, Fabio Ramos, Lionel Ott |
| Abstract | Sensors producing 3D point clouds such as 3D laser scanners and RGB-D cameras are widely used in robotics, be it for autonomous driving or manipulation. Aligning point clouds produced by these sensors is a vital component in such applications to perform tasks such as model registration, pose estimation, and SLAM. Iterative closest point (ICP) is the most widely used method for this task, due to its simplicity and efficiency. In this paper we propose a novel method which solves the optimisation problem posed by ICP using stochastic gradient descent (SGD). Using SGD allows us to improve the convergence speed of ICP without sacrificing solution quality. Experiments using Kinect as well as Velodyne data show that, our proposed method is faster than existing methods, while obtaining solutions comparable to standard ICP. An additional benefit is robustness to parameters when processing data from different sensors. |
| Tasks | Autonomous Driving, Pose Estimation |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09133v1 |
| https://arxiv.org/pdf/1907.09133v1.pdf | |
| PWC | https://paperswithcode.com/paper/speeding-up-iterative-closest-point-using |
| Repo | |
| Framework | |
Exploring the Semantics for Visual Relationship Detection
| Title | Exploring the Semantics for Visual Relationship Detection |
| Authors | Wentong Liao, Cuiling Lan, Wenjun Zeng, Michael Ying Yang, Bodo Rosenhahn |
| Abstract | Scene graph construction / visual relationship detection from an image aims to give a precise structural description of the objects (nodes) and their relationships (edges). The mutual promotion of object detection and relationship detection is important for enhancing their individual performance. In this work, we propose a new framework, called semantics guided graph relation neural network (SGRN), for effective visual relationship detection. First, to boost the object detection accuracy, we introduce a source-target class cognoscitive transformation that transforms the features of the co-occurent objects to the target object domain to refine the visual features. Similarly, source-target cognoscitive transformations are used to refine features of objects from features of relations, and vice versa. Second, to boost the relation detection accuracy, besides the visual features of the paired objects, we embed the class probability of the object and subject separately to provide high level semantic information. In addition, to reduce the search space of relationships, we design a semantics-aware relationship filter to exclude those object pairs that have no relation. We evaluate our approach on the Visual Genome dataset and it achieves the state-of-the-art performance for visual relationship detection. Additionally, Our approach also significantly improves the object detection performance (i.e. 4.2% in mAP accuracy). |
| Tasks | graph construction, Object Detection |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.02104v1 |
| http://arxiv.org/pdf/1904.02104v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-the-semantics-for-visual |
| Repo | |
| Framework | |
Mincut pooling in Graph Neural Networks
| Title | Mincut pooling in Graph Neural Networks |
| Authors | Filippo Maria Bianchi, Daniele Grattarola, Cesare Alippi |
| Abstract | The advance of node pooling operations in Graph Neural Networks (GNNs) has lagged behind the feverish design of new message-passing techniques, and pooling remains an important and challenging endeavor for the design of deep architectures. In this paper, we propose a pooling operation for GNNs that leverages a differentiable unsupervised loss based on the mincut optimization objective. For each node, our method learns a soft cluster assignment vector that depends on the node features, the target inference task (e.g., graph classification), and, thanks to the mincut objective, also on the graph connectivity. Graph pooling is obtained by applying the matrix of assignment vectors to the adjacency matrix and the node features. We validate the effectiveness of the proposed pooling method on a variety of supervised and unsupervised tasks. |
| Tasks | Graph Classification, Semantic Segmentation |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00481v2 |
| https://arxiv.org/pdf/1907.00481v2.pdf | |
| PWC | https://paperswithcode.com/paper/mincut-pooling-in-graph-neural-networks |
| Repo | |
| Framework | |
HOG feature extraction from encrypted images for privacy-preserving machine learning
| Title | HOG feature extraction from encrypted images for privacy-preserving machine learning |
| Authors | Masaki Kitayama, Hitoshi Kiya |
| Abstract | In this paper, we propose an extraction method of HOG (histograms-of-oriented-gradients) features from encryption-then-compression (EtC) images for privacy-preserving machine learning, where EtC images are images encrypted by a block-based encryption method proposed for EtC systems with JPEG compression, and HOG is a feature descriptor used in computer vision for the purpose of object detection and image classification. Recently, cloud computing and machine learning have been spreading in many fields. However, the cloud computing has serious privacy issues for end users, due to unreliability of providers and some accidents. Accordingly, we propose a novel block-based extraction method of HOG features, and the proposed method enables us to carry out any machine learning algorithms without any influence, under some conditions. In an experiment, the proposed method is applied to a face image recognition problem under the use of two kinds of classifiers: linear support vector machine (SVM), gaussian SVM, to demonstrate the effectiveness. |
| Tasks | Image Classification, Object Detection |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12434v1 |
| http://arxiv.org/pdf/1904.12434v1.pdf | |
| PWC | https://paperswithcode.com/paper/hog-feature-extraction-from-encrypted-images |
| Repo | |
| Framework | |
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
| Title | Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs |
| Authors | Max Simchowitz, Kevin Jamieson |
| Abstract | This paper establishes that optimistic algorithms attain gap-dependent and non-asymptotic logarithmic regret for episodic MDPs. In contrast to prior work, our bounds do not suffer a dependence on diameter-like quantities or ergodicity, and smoothly interpolate between the gap dependent logarithmic-regret, and the $\widetilde{\mathcal{O}}(\sqrt{HSAT})$-minimax rate. The key technique in our analysis is a novel “clipped” regret decomposition which applies to a broad family of recent optimistic algorithms for episodic MDPs. |
| Tasks | |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03814v2 |
| https://arxiv.org/pdf/1905.03814v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-asymptotic-gap-dependent-regret-bounds |
| Repo | |
| Framework | |
Attacking Graph Convolutional Networks via Rewiring
| Title | Attacking Graph Convolutional Networks via Rewiring |
| Authors | Yao Ma, Suhang Wang, Tyler Derr, Lingfei Wu, Jiliang Tang |
| Abstract | Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which deliberately add carefully created unnoticeable perturbation to the graph structure. The perturbation is usually created by adding/deleting a few edges, which might be noticeable even when the number of edges modified is small. In this paper, we propose a graph rewiring operation which affects the graph in a less noticeable way compared to adding/deleting edges. We then use reinforcement learning to learn the attack strategy based on the proposed rewiring operation. Experiments on real world graphs demonstrate the effectiveness of the proposed framework. To understand the proposed framework, we further analyze how its generated perturbation to the graph structure affects the output of the target model. |
| Tasks | Graph Classification, Node Classification |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03750v2 |
| https://arxiv.org/pdf/1906.03750v2.pdf | |
| PWC | https://paperswithcode.com/paper/attacking-graph-convolutional-networks-via |
| Repo | |
| Framework | |
Model-Free Model Reconciliation
| Title | Model-Free Model Reconciliation |
| Authors | Sarath Sreedharan, Alberto Olmo, Aditya Prasad Mishra, Subbarao Kambhampati |
| Abstract | Designing agents capable of explaining complex sequential decisions remain a significant open problem in automated decision-making. Recently, there has been a lot of interest in developing approaches for generating such explanations for various decision-making paradigms. One such approach has been the idea of {\em explanation as model-reconciliation}. The framework hypothesizes that one of the common reasons for the user’s confusion could be the mismatch between the user’s model of the task and the one used by the system to generate the decisions. While this is a general framework, most works that have been explicitly built on this explanatory philosophy have focused on settings where the model of user’s knowledge is available in a declarative form. Our goal in this paper is to adapt the model reconciliation approach to the cases where such user models are no longer explicitly provided. We present a simple and easy to learn labeling model that can help an explainer decide what information could help achieve model reconciliation between the user and the agent. |
| Tasks | Decision Making |
| Published | 2019-03-17 |
| URL | http://arxiv.org/abs/1903.07198v1 |
| http://arxiv.org/pdf/1903.07198v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-free-model-reconciliation |
| Repo | |
| Framework | |
The role of ego vision in view-invariant action recognition
| Title | The role of ego vision in view-invariant action recognition |
| Authors | Gaurvi Goyal, Nicoletta Noceti, Francesca Odone, Alessandra Sciutti |
| Abstract | Analysis and interpretation of egocentric video data is becoming more and more important with the increasing availability and use of wearable cameras. Exploring and fully understanding affinities and differences between ego and allo (or third-person) vision is paramount for the design of effective methods to process, analyse and interpret egocentric data. In addition, a deeper understanding of ego-vision and its peculiarities may enable new research perspectives in which first person viewpoints can act either as a mean for easily acquiring large amounts of data to be employed in general-purpose recognition systems, and as a challenging test-bed to assess the usability of techniques specifically tailored to deal with allocentric vision on more challenging settings. Our work, with an eye to cognitive science findings, leverages transfer learning in Convolutional Neural Networks to demonstrate capabilities and limitations of an implicitly learnt view-invariant representation in the specific case of action recognition. |
| Tasks | Transfer Learning |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03918v1 |
| https://arxiv.org/pdf/1906.03918v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-role-of-ego-vision-in-view-invariant |
| Repo | |
| Framework | |
Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forget
| Title | Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forget |
| Authors | Guy Davidson, Michael C. Mozer |
| Abstract | We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned tasks. This setting corresponds to that which human learners face as they acquire domain expertise serially, for example, as an individual studies a textbook. Through simulations involving sequences of ten related visual tasks, we find reason for optimism that nets will scale well as they advance from having a single skill to becoming multi-skill domain experts. We observe two key phenomena. First, \emph{forward facilitation}—the accelerated learning of task $n+1$ having learned $n$ previous tasks—grows with $n$. Second, \emph{backward interference}—the forgetting of the $n$ previous tasks when learning task $n+1$—diminishes with $n$. Amplifying forward facilitation is the goal of research on metalearning, and attenuating backward interference is the goal of research on catastrophic forgetting. We find that both of these goals are attained simply through broader exposure to a domain. |
| Tasks | Continual Learning |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.10837v5 |
| https://arxiv.org/pdf/1905.10837v5.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-mastery-of-multiple-tasks-networks |
| Repo | |
| Framework | |
