Recently proposed encoder-decoder structures for modeling Hawkes processes use transformer-inspired architectures, which encode the history of events via embeddings and self-attention mechanisms. These models deliver better prediction and goodness-of-fit than their RNN-based counterparts. However, they often require high computational and memory complexity requirements and sometimes fail to adequately capture the triggering function of the underlying process. So motivated, we introduce an efficient and general encoding of the historical event sequence by replacing the complex (multilayered) attention structures with triggering kernels of the observed data. Noting the similarity between the triggering kernels of a point process and the attention scores, we use a triggering kernel to replace the weights used to build history representations. Our estimate for the triggering function is equipped with a sigmoid gating mechanism that captures local-in-time triggering effects that are otherwise challenging with standard decaying-over-time kernels. Further, taking both event type representations and temporal embeddings as inputs, the model learns the underlying triggering type-time kernel parameters given pairs of event types. We present experiments on synthetic and real data sets widely used by competing models, while further including a COVID-19 dataset to illustrate a scenario where longitudinal covariates are available. Results show the proposed model outperforms existing approaches while being more efficient in terms of computational complexity and yielding interpretable results via direct application of the newly introduced kernel.
相關內容
Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already learned while updating their parameters in absence of the original training data. Previous works extended standard classification methods in the object detection task, mainly adopting the knowledge distillation framework. However, we argue that object detection introduces an additional problem, which has been overlooked. While objects belonging to new classes are learned thanks to their annotations, if no supervision is provided for other objects that may still be present in the input, the model learns to associate them to background regions. We propose to handle these missing annotations by revisiting the standard knowledge distillation framework. Our approach outperforms current state-of-the-art methods in every setting of the Pascal-VOC dataset. We further propose an extension to instance segmentation, outperforming the other baselines. In this work, we propose to handle the missing annotations by revisiting the standard knowledge distillation framework. We show that our approach outperforms current state-of-the-art methods in every setting of the Pascal-VOC 2007 dataset. Moreover, we propose a simple extension to instance segmentation, showing that it outperforms the other baselines.
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers could improve the performance, yet the inner-modal attentive weights may also be diluted, which could thus undermine the final performance. In this paper, we propose a multimodal token fusion method (TokenFusion), tailored for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and substitutes these tokens with projected and aggregated inter-modal features. Residual positional alignment is also adopted to enable explicit utilization of the inter-modal alignments after fusion. The design of TokenFusion allows the transformer to learn correlations among multimodal features, while the single-modal transformer architecture remains largely intact. Extensive experiments are conducted on a variety of homogeneous and heterogeneous modalities and demonstrate that TokenFusion surpasses state-of-the-art methods in three typical vision tasks: multimodal image-to-image translation, RGB-depth semantic segmentation, and 3D object detection with point cloud and images.
Recent advancements in location-aware analytics have created novel opportunities in different domains. In the area of process mining, enriching process models with geolocation helps to gain a better understanding of how the process activities are executed in practice. In this paper, we introduce our idea of geo-enabled process modeling and report on our industrial experience. To this end, we present a real-world case study to describe the importance of considering the location in process mining. Then we discuss the shortcomings of currently available process mining tools and propose our novel approach for modeling geo-enabled processes focusing on 1) increasing process interpretability through geo-visualization, 2) incorporating location-related metadata into process analysis, and 3) using location-based measures for the assessment of process performance. Finally, we conclude the paper by future research directions.
As a crucial component of most modern deep recommender systems, feature embedding maps high-dimensional sparse user/item features into low-dimensional dense embeddings. However, these embeddings are usually assigned a unified dimension, which suffers from the following issues: (1) high memory usage and computation cost. (2) sub-optimal performance due to inferior dimension assignments. In order to alleviate the above issues, some works focus on automated embedding dimension search by formulating it as hyper-parameter optimization or embedding pruning problems. However, they either require well-designed search space for hyperparameters or need time-consuming optimization procedures. In this paper, we propose a Single-Shot Embedding Dimension Search method, called SSEDS, which can efficiently assign dimensions for each feature field via a single-shot embedding pruning operation while maintaining the recommendation accuracy of the model. Specifically, it introduces a criterion for identifying the importance of each embedding dimension for each feature field. As a result, SSEDS could automatically obtain mixed-dimensional embeddings by explicitly reducing redundant embedding dimensions based on the corresponding dimension importance ranking and the predefined parameter budget. Furthermore, the proposed SSEDS is model-agnostic, meaning that it could be integrated into different base recommendation models. The extensive offline experiments are conducted on two widely used public datasets for CTR prediction tasks, and the results demonstrate that SSEDS can still achieve strong recommendation performance even if it has reduced 90\% parameters. Moreover, SSEDS has also been deployed on the WeChat Subscription platform for practical recommendation services. The 7-day online A/B test results show that SSEDS can significantly improve the performance of the online recommendation model.
Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a high prediction capacity of the model, which is the ability to capture precise long-range dependency coupling between output and input efficiently. Recent studies have shown the potential of Transformer to increase the prediction capacity. However, there are several severe issues with Transformer that prevent it from being directly applicable to LSTF, such as quadratic time complexity, high memory usage, and inherent limitation of the encoder-decoder architecture. To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a $ProbSparse$ Self-attention mechanism, which achieves $O(L \log L)$ in time complexity and memory usage, and has comparable performance on sequences' dependency alignment. (ii) the self-attention distilling highlights dominating attention by halving cascading layer input, and efficiently handles extreme long input sequences. (iii) the generative style decoder, while conceptually simple, predicts the long time-series sequences at one forward operation rather than a step-by-step way, which drastically improves the inference speed of long-sequence predictions. Extensive experiments on four large-scale datasets demonstrate that Informer significantly outperforms existing methods and provides a new solution to the LSTF problem.
Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node- and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations for different types of nodes and edges. To handle dynamic heterogeneous graphs, we introduce the relative temporal encoding technique into HGT, which is able to capture the dynamic structural dependency with arbitrary durations. To handle Web-scale graph data, we design the heterogeneous mini-batch graph sampling algorithm---HGSampling---for efficient and scalable training. Extensive experiments on the Open Academic Graph of 179 million nodes and 2 billion edges show that the proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9%--21% on various downstream tasks.
Clustering is one of the most fundamental and wide-spread techniques in exploratory data analysis. Yet, the basic approach to clustering has not really changed: a practitioner hand-picks a task-specific clustering loss to optimize and fit the given data to reveal the underlying cluster structure. Some types of losses---such as k-means, or its non-linear version: kernelized k-means (centroid based), and DBSCAN (density based)---are popular choices due to their good empirical performance on a range of applications. Although every so often the clustering output using these standard losses fails to reveal the underlying structure, and the practitioner has to custom-design their own variation. In this work we take an intrinsically different approach to clustering: rather than fitting a dataset to a specific clustering loss, we train a recurrent model that learns how to cluster. The model uses as training pairs examples of datasets (as input) and its corresponding cluster identities (as output). By providing multiple types of training datasets as inputs, our model has the ability to generalize well on unseen datasets (new clustering tasks). Our experiments reveal that by training on simple synthetically generated datasets or on existing real datasets, we can achieve better clustering performance on unseen real-world datasets when compared with standard benchmark clustering techniques. Our meta clustering model works well even for small datasets where the usual deep learning models tend to perform worse.
Event detection (ED), a sub-task of event extraction, involves identifying triggers and categorizing event mentions. Existing methods primarily rely upon supervised learning and require large-scale labeled event datasets which are unfortunately not readily available in many real-life applications. In this paper, we consider and reformulate the ED task with limited labeled data as a Few-Shot Learning problem. We propose a Dynamic-Memory-Based Prototypical Network (DMB-PN), which exploits Dynamic Memory Network (DMN) to not only learn better prototypes for event types, but also produce more robust sentence encodings for event mentions. Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs. The experiments show that DMB-PN not only deals with sample scarcity better than a series of baseline models but also performs more robustly when the variety of event types is relatively large and the instance quantity is extremely small.
In structure learning, the output is generally a structure that is used as supervision information to achieve good performance. Considering the interpretation of deep learning models has raised extended attention these years, it will be beneficial if we can learn an interpretable structure from deep learning models. In this paper, we focus on Recurrent Neural Networks (RNNs) whose inner mechanism is still not clearly understood. We find that Finite State Automaton (FSA) that processes sequential data has more interpretable inner mechanism and can be learned from RNNs as the interpretable structure. We propose two methods to learn FSA from RNN based on two different clustering methods. We first give the graphical illustration of FSA for human beings to follow, which shows the interpretability. From the FSA's point of view, we then analyze how the performance of RNNs are affected by the number of gates, as well as the semantic meaning behind the transition of numerical hidden states. Our results suggest that RNNs with simple gated structure such as Minimal Gated Unit (MGU) is more desirable and the transitions in FSA leading to specific classification result are associated with corresponding words which are understandable by human beings.
We introduce the first system towards the novel task of answering complex multisentence recommendation questions in the tourism domain. Our solution uses a pipeline of two modules: question understanding and answering. For question understanding, we define an SQL-like query language that captures the semantic intent of a question; it supports operators like subset, negation, preference and similarity, which are often found in recommendation questions. We train and compare traditional CRFs as well as bidirectional LSTM-based models for converting a question to its semantic representation. We extend these models to a semisupervised setting with partially labeled sequences gathered through crowdsourcing. We find that our best model performs semi-supervised training of BiDiLSTM+CRF with hand-designed features and CCM(Chang et al., 2007) constraints. Finally, in an end to end QA system, our answering component converts our question representation into queries fired on underlying knowledge sources. Our experiments on two different answer corpora demonstrate that our system can significantly outperform baselines with up to 20 pt higher accuracy and 17 pt higher recall.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191