Jiajun Liu

Yanping Zheng, Hanzhi Wang, Zhewei Wei et al.

Graph Neural Networks (GNNs) have been widely used for modeling graph-structured data. With the development of numerous GNN variants, recent years have witnessed groundbreaking results in improving the scalability of GNNs to work on static graphs with millions of nodes. However, how to instantly represent continuous changes of large-scale dynamic graphs with GNNs is still an open problem. Existing dynamic GNNs focus on modeling the periodic evolution of graphs, often on a snapshot basis. Such methods suffer from two drawbacks: first, there is a substantial delay for the changes in the graph to be reflected in the graph representations, resulting in losses on the model's accuracy; second, repeatedly calculating the representation matrix on the entire graph in each snapshot is predominantly time-consuming and severely limits the scalability. In this paper, we propose Instant Graph Neural Network (InstantGNN), an incremental computation approach for the graph representation matrix of dynamic graphs. Set to work with dynamic graphs with the edge-arrival model, our method avoids time-consuming, repetitive computations and allows instant updates on the representation and instant predictions. Graphs with dynamic structures and dynamic attributes are both supported. The upper bounds of time complexity of those updates are also provided. Furthermore, our method provides an adaptive training strategy, which guides the model to retrain at moments when it can make the greatest performance gains. We conduct extensive experiments on several real-world and synthetic datasets. Empirical results demonstrate that our model achieves state-of-the-art accuracy while having orders-of-magnitude higher efficiency than existing methods.

Yudong Chen, Sen Wang, Jiajun Liu et al.

In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains under-explored. In this paper, we first discuss a plausible mechanism of the projector with empirical evidence and then propose a new feature distillation method based on a projector ensemble for further performance improvement. We observe that the student network benefits from a projector even if the feature dimensions of the student and the teacher are the same. Training a student backbone without a projector can be considered as a multi-task learning process, namely achieving discriminative feature extraction for classification and feature matching between the student and the teacher for distillation at the same time. We hypothesize and empirically verify that without a projector, the student network tends to overfit the teacher's feature distributions despite having different architecture and weights initialization. This leads to degradation on the quality of the student's deep features that are eventually used in classification. Adding a projector, on the other hand, disentangles the two learning tasks and helps the student network to focus better on the main feature extraction task while still being able to utilize teacher features as a guidance through the projector. Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features. Experimental results on different datasets with a series of teacher-student pairs illustrate the effectiveness of the proposed method.

Yudong Chen, Sen Wang, Jiajun Liu et al.

Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimension mismatch between the teacher and the student networks. Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance. In addition, projectors even improve logit distillation if we add them to the architecture too. Inspired by these surprising findings and the general lack of understanding of the projectors in the knowledge distillation process from existing literature, this paper investigates the implicit role that projectors play but so far have been overlooked. Our empirical study shows that the student with a projector (1) obtains a better trade-off between the training accuracy and the testing accuracy compared to the student without a projector when it has the same feature dimensions as the teacher, (2) better preserves its similarity to the teacher beyond shallow and numeric resemblance, from the view of Centered Kernel Alignment (CKA), and (3) avoids being over-confident as the teacher does at the testing phase. Motivated by the positive effects of projectors, we propose a projector ensemble-based feature distillation method to further improve distillation performance. Despite the simplicity of the proposed strategy, empirical results from the evaluation of classification tasks on benchmark datasets demonstrate the superior classification performance of our method on a broad range of teacher-student pairs and verify from the aspects of CKA and model calibration that the student's features are of improved quality with the projector ensemble design.

Haodong Hong, Sen Wang, Zi Huang et al.

Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be associated with different visual signals, causing severe ambiguity and limiting the transfer of prior knowledge in the vision domain from the user to the agent. To fill this gap, we propose Vision-and-Language Navigation with Multi-modal Prompts (VLN-MP), a novel task augmenting traditional VLN by integrating both natural language and images in instructions. VLN-MP not only maintains backward compatibility by effectively handling text-only prompts but also consistently shows advantages with different quantities and relevance of visual prompts. Possible forms of visual prompts include both exact and similar object images, providing adaptability and versatility in diverse navigation scenarios. To evaluate VLN-MP under a unified framework, we implement a new benchmark that offers: (1) a training-free pipeline to transform textual instructions into multi-modal forms with landmark images; (2) diverse datasets with multi-modal instructions for different downstream tasks; (3) a novel module designed to process various image prompts for seamless integration with state-of-the-art VLN models. Extensive experiments on four VLN benchmarks (R2R, RxR, REVERIE, CVDN) show that incorporating visual prompts significantly boosts navigation performance. While maintaining efficiency with text-only prompts, VLN-MP enables agents to navigate in the pre-explore setting and outperform text-based models, showing its broader applicability.

Yanping Zheng, Zhewei Wei, Jiajun Liu

Real-world graphs, such as social networks, financial transactions, and recommendation systems, often demonstrate dynamic behavior. This phenomenon, known as graph stream, involves the dynamic changes of nodes and the emergence and disappearance of edges. To effectively capture both the structural and temporal aspects of these dynamic graphs, dynamic graph neural networks have been developed. However, existing methods are usually tailored to process either continuous-time or discrete-time dynamic graphs, and cannot be generalized from one to the other. In this paper, we propose a decoupled graph neural network for large dynamic graphs, including a unified dynamic propagation that supports efficient computation for both continuous and discrete dynamic graphs. Since graph structure-related computations are only performed during the propagation process, the prediction process for the downstream task can be trained separately without expensive graph computations, and therefore any sequence model can be plugged-in and used. As a result, our algorithm achieves exceptional scalability and expressiveness. We evaluate our algorithm on seven real-world datasets of both continuous-time and discrete-time dynamic graphs. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in both kinds of dynamic graphs. Most notably, the scalability of our algorithm is well illustrated by its successful application to large graphs with up to over a billion temporal edges and over a hundred million nodes.

Thejan Rajapakshe, Rajib Rana, Sara Khalifa et al.

Reinforcement Learning (RL) is a semi-supervised learning paradigm which an agent learns by interacting with an environment. Deep learning in combination with RL provides an efficient method to learn how to interact with the environment is called Deep Reinforcement Learning (deep RL). Deep RL has gained tremendous success in gaming - such as AlphaGo, but its potential have rarely being explored for challenging tasks like Speech Emotion Recognition (SER). The deep RL being used for SER can potentially improve the performance of an automated call centre agent by dynamically learning emotional-aware response to customer queries. While the policy employed by the RL agent plays a major role in action selection, there is no current RL policy tailored for SER. In addition, extended learning period is a general challenge for deep RL which can impact the speed of learning for SER. Therefore, in this paper, we introduce a novel policy - "Zeta policy" which is tailored for SER and apply Pre-training in deep RL to achieve faster learning rate. Pre-training with cross dataset was also studied to discover the feasibility of pre-training the RL Agent with a similar dataset in a scenario of where no real environmental data is not available. IEMOCAP and SAVEE datasets were used for the evaluation with the problem being to recognize four emotions happy, sad, angry and neutral in the utterances provided. Experimental results show that the proposed "Zeta policy" performs better than existing policies. The results also support that pre-training can reduce the training time upon reducing the warm-up period and is robust to cross-corpus scenario.

Guoping Zhao, Mingyu Zhang, Jiajun Liu et al.

Studies show that Deep Neural Network (DNN)-based image classification models are vulnerable to maliciously constructed adversarial examples. However, little effort has been made to investigate how DNN-based image retrieval models are affected by such attacks. In this paper, we introduce Unsupervised Adversarial Attacks with Generative Adversarial Networks (UAA-GAN) to attack deep feature-based image retrieval systems. UAA-GAN is an unsupervised learning model that requires only a small amount of unlabeled data for training. Once trained, it produces query-specific perturbations for query images to form adversarial queries. The core idea is to ensure that the attached perturbation is barely perceptible to human yet effective in pushing the query away from its original position in the deep feature space. UAA-GAN works with various application scenarios that are based on deep features, including image retrieval, person Re-ID and face search. Empirical results show that UAA-GAN cripples retrieval performance without significant visual changes in the query images. UAA-GAN generated adversarial examples are less distinguishable because they tend to incorporate subtle perturbations in textured or salient areas of the images, such as key body parts of human, dominant structural patterns/textures or edges, rather than in visually insignificant areas (e.g., background and sky). Such tendency indicates that the model indeed learned how to toy with both image retrieval systems and human eyes.

Yanlei Yu, Zhiwu Lu, Jiajun Liu et al.

We have witnessed the discovery of many techniques for network representation learning in recent years, ranging from encoding the context in random walks to embedding the lower order connections, to finding latent space representations with auto-encoders. However, existing techniques are looking mostly into the local structures in a network, while higher-level properties such as global community structures are often neglected. We propose a novel network representations learning model framework called RUM (network Representation learning throUgh Multi-level structural information preservation). In RUM, we incorporate three essential aspects of a node that capture a network's characteristics in multiple levels: a node's affiliated local triads, its neighborhood relationships, and its global community affiliations. Therefore the framework explicitly and comprehensively preserves the structural information of a network, extending the encoding process both to the local end of the structural information spectrum and to the global end. The framework is also flexible enough to take various community discovery algorithms as its preprocessor. Empirical results show that the representations learned by RUM have demonstrated substantial performance advantages in real-life tasks.

Lianli Gao, Jingkuan Song, Xingyi Liu et al.

During the last decade, the deluge of multimedia data has impacted a wide range of research areas, including multimedia retrieval, 3D tracking, database management, data mining, machine learning, social media analysis, medical imaging, and so on. Machine learning is largely involved in multimedia applications of building models for classification and regression tasks etc., and the learning principle consists in designing the models based on the information contained in the multimedia dataset. While many paradigms exist and are widely used in the context of machine learning, most of them suffer from the `curse of dimensionality', which means that some strange phenomena appears when data are represented in a high-dimensional space. Given the high dimensionality and the high complexity of multimedia data, it is important to investigate new machine learning algorithms to facilitate multimedia data analysis. To deal with the impact of high dimensionality, an intuitive way is to reduce the dimensionality. On the other hand, some researchers devoted themselves to designing some effective learning schemes for high-dimensional data. In this survey, we cover feature transformation, feature selection and feature encoding, three approaches fighting the consequences of the curse of dimensionality. Next, we briefly introduce some recent progress of effective learning algorithms. Finally, promising future trends on multimedia learning are envisaged.

Jiajun Liu, Kun Zhao, Brano Kusy et al.

The prediction of periodical time-series remains challenging due to various types of data distortions and misalignments. Here, we propose a novel model called Temporal embedding-enhanced convolutional neural Network (TeNet) to learn repeatedly-occurring-yet-hidden structural elements in periodical time-series, called abstract snippets, for predicting future changes. Our model uses convolutional neural networks and embeds a time-series with its potential neighbors in the temporal domain for aligning it to the dominant patterns in the dataset. The model is robust to distortions and misalignments in the temporal domain and demonstrates strong prediction power for periodical time-series. We conduct extensive experiments and discover that the proposed model shows significant and consistent advantages over existing methods on a variety of data modalities ranging from human mobility to household power consumption records. Empirical results indicate that the model is robust to various factors such as number of samples, variance of data, numerical ranges of data etc. The experiments also verify that the intuition behind the model can be generalized to multiple data types and applications and promises significant improvement in prediction performances across the datasets studied.