We propose a simple, fast, and accurate one-stage approach to visual grounding, inspired by the following insight. The performances of existing propose-and-rank two-stage methods are capped by the quality of the region candidates they propose in the first stage --- if none of the candidates could cover the ground truth region, there is no hope in the second stage to rank the right region to the top. To avoid this caveat, we propose a one-stage model that enables end-to-end joint optimization. The main idea is as straightforward as fusing a text query's embedding into the YOLOv3 object detector, augmented by spatial features so as to account for spatial mentions in the query. Despite being simple, this one-stage approach shows great potential in terms of both accuracy and speed for both phrase localization and referring expression comprehension, according to our experiments. Given these results along with careful investigations into some popular region proposals, we advocate for visual grounding a paradigm shift from the conventional two-stage methods to the one-stage framework.
With the great success of Graph Neural Networks (GNNs) towards representation learning on graph-structure data, the robustness of GNNs against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless of the fruitful progress, current works suffer from two main limitations: First, the attack method required to be developed case by case; Second, most of them are restricted to the white-box attack. This paper promotes current frameworks in a more general and flexible sense -- we demand only one single method to attack various kinds of GNNs and this attacker is black box driven. To this end, we begin by investigating the theoretical connections between different kinds of GNNs in a principled way and integrate different GNN models into a unified framework, dubbed as General Spectral Graph Convolution. As such, a generalized adversarial attacker is proposed towards two families of GNNs: Convolution-based model and sampling-based model. More interestingly, our attacker does not require any knowledge of the target classifiers used in GNNs. Extensive experimental results validate the effectiveness of our method on several benchmark datasets. Particularly by using our attack, even small graph perturbations like one-edge flip is able to consistently make a strong attack in performance to different GNN models.
Existing Graph Convolutional Networks (GCNs) are shallow---the number of the layers is usually not larger than 2. The deeper variants by simply stacking more layers, unfortunately perform worse, even involving well-known tricks like weight penalizing, dropout, and residual connections. This paper reveals that developing deep GCNs mainly encounters two obstacles: \emph{over-fitting} and \emph{over-smoothing}. The over-fitting issue weakens the generalization ability on small graphs, while over-smoothing impedes model training by isolating output representations from the input features with the increase in network depth. Hence, we propose DropEdge, a novel technique to alleviate both issues. At its core, DropEdge randomly removes a certain number of edges from the input graphs, acting like a data augmenter and also a message passing reducer. More importantly, DropEdge enables us to recast a wider range of Convolutional Neural Networks (CNNs) from the image field to the graph domain; in particular, we study DenseNet and InceptionNet in this paper. Extensive experiments on several benchmarks demonstrate that our method allows deep GCNs to achieve promising performance, even when the number of layers exceeds 30---the deepest GCN that has ever been proposed.
Graph classification is practically important in many domains. To solve this problem, one usually calculates a low-dimensional representation for each node in the graph with supervised or unsupervised approaches. Most existing approaches consider all the edges between nodes while overlooking whether the edge will brings positive or negative influence to the node representation learning. In many real-world applications, however, some connections among the nodes can be noisy for graph convolution, and not all the edges deserve your attention. In this work, we distinguish the positive and negative impacts of the neighbors to the node in graph node classification, and propose to enhance the graph convolutional network by considering the labels between the neighbor edges. We present a novel GCN framework, called Label-aware Graph Convolutional Network (LAGCN), which incorporates the supervised and unsupervised learning by introducing the edge label predictor. As a general model, LAGCN can be easily adapted in various previous GCN and enhance their performance with some theoretical guarantees. Experimental results on multiple real-world datasets show that LAGCN is competitive against various state-of-the-art methods in graph classification.
Graph alignment, also known as network alignment, is a fundamental task in social network analysis. Many recent works have relied on partially labeled cross-graph node correspondences, i.e., anchor links. However, due to the privacy and security issue, the manual labeling of anchor links for diverse scenarios may be prohibitive. Aligning two graphs without any anchor links is a crucial and challenging task. In this paper, we propose an Unsupervised Adversarial Graph Alignment (UAGA) framework to learn a cross-graph alignment between two embedding spaces of different graphs in a fully unsupervised fashion (\emph{i.e.,} no existing anchor links and no users' personal profile or attribute information is available). The proposed framework learns the embedding spaces of each graph, and then attempts to align the two spaces via adversarial training, followed by a refinement procedure. We further extend our UAGA method to incremental UAGA (iUAGA) that iteratively reveals the unobserved user links based on the pseudo anchor links. This can be used to further improve both the embedding quality and the alignment accuracy. Moreover, the proposed methods will benefit some real-world applications, \emph{e.g.,} link prediction in social networks. Comprehensive experiments on real-world data demonstrate the effectiveness of our proposed approaches UAGA and iUAGA for unsupervised graph alignment.
Graph representation on large-scale bipartite graphs is central for a variety of applications, ranging from social network analysis to recommendation system development. Existing methods exhibit two key drawbacks: 1. unable to characterize the inconsistency of the node features within the bipartite-specific structure; 2. unfriendly to support large-scale bipartite graphs. To this end, we propose ABCGraph, a scalable model for unsupervised learning on large-scale bipartite graphs. At its heart, ABCGraph utilizes the proposed Bipartite Graph Convolutional Network (BGCN) as the encoder and adversarial learning as the training loss to learn representations from nodes in two different domains and bipartite structures, in an unsupervised manner. Moreover, we devise a cascaded architecture to capture the multi-hop relationship in bipartite structure and improves the scalability as well. Extensive experiments on multiple datasets of varying scales verify the effectiveness of ABCGraph compared to state-of-the-arts. For the experiment on a real-world large-scale bipartite graph system, fast training speed and low memory cost demonstrate the scalability of ABCGraph model.
We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces. In contrast to previous attempts, our model runs without the aid of spectral clustering. This makes our algorithm one of the kinds that can gracefully scale to large datasets. At its heart, our neural model benefits from a classifier which determines whether a pair of points lies on the same subspace or not. Essential to our model is the construction of two affinity matrices, one from the classifier and the other from a notion of subspace self-expressiveness, to supervise training in a collaborative scheme. We thoroughly assess and contrast the performance of our model against various state-of-the-art clustering algorithms including deep subspace-based ones.
Node classification and graph classification are two graph learning problems that predict the class label of a node and the class label of a graph respectively. A node of a graph usually represents a real-world entity, e.g., a user in a social network, or a protein in a protein-protein interaction network. In this work, we consider a more challenging but practically useful setting, in which a node itself is a graph instance. This leads to a hierarchical graph perspective which arises in many domains such as social network, biological network and document collection. For example, in a social network, a group of people with shared interests forms a user group, whereas a number of user groups are interconnected via interactions or common members. We study the node classification problem in the hierarchical graph where a `node' is a graph instance, e.g., a user group in the above example. As labels are usually limited in real-world data, we design two novel semi-supervised solutions named \underline{SE}mi-supervised gr\underline{A}ph c\underline{L}assification via \underline{C}autious/\underline{A}ctive \underline{I}teration (or SEAL-C/AI in short). SEAL-C/AI adopt an iterative framework that takes turns to build or update two classifiers, one working at the graph instance level and the other at the hierarchical graph level. To simplify the representation of the hierarchical graph, we propose a novel supervised, self-attentive graph embedding method called SAGE, which embeds graph instances of arbitrary size into fixed-length vectors. Through experiments on synthetic data and Tencent QQ group data, we demonstrate that SEAL-C/AI not only outperform competing methods by a significant margin in terms of accuracy/Macro-F1, but also generate meaningful interpretations of the learned representations.
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on target task, both of which, however, are inconvenient to obtain in practice. In this paper, we relax these two strong conditions by developing a novel task transfer framework where the expert preference is applied as a guidance. In particular, we alternate the following two steps: Firstly, letting experts apply pre-defined preference rules to select related expert demonstrates for the target task. Secondly, based on the selection result, we learn the target cost function and trajectory distribution simultaneously via enhanced Adversarial MaxEnt IRL and generate more trajectories by the learned target distribution for the next preference selection. The theoretical analysis on the distribution learning and convergence of the proposed algorithm are provided. Extensive simulations on several benchmarks have been conducted for further verifying the effectiveness of the proposed method.
Dense event captioning aims to detect and describe all events of interest contained in a video. Despite the advanced development in this area, existing methods tackle this task by making use of dense temporal annotations, which is dramatically source-consuming. This paper formulates a new problem: weakly supervised dense event captioning, which does not require temporal segment annotations for model training. Our solution is based on the one-to-one correspondence assumption, each caption describes one temporal segment, and each temporal segment has one caption, which holds in current benchmark datasets and most real-world cases. We decompose the problem into a pair of dual problems: event captioning and sentence localization and present a cycle system to train our model. Extensive experimental results are provided to demonstrate the ability of our model on both dense event captioning and sentence localization in videos.