This paper presents the foundational elements of a distributed memory method for mesh generation that is designed to leverage concurrency offered by large-scale computing. To achieve this goal, meshing functionality is separated from performance aspects by utilizing a separate entity for each - a shared memory mesh generation code called CDT3D and PREMA for parallel runtime support. Although CDT3D is designed for scalability, lessons are presented regarding additional measures that were taken to enable the code's integration into the distributed memory method as a black box. In the presented method, an initial mesh is data decomposed and subdomains are distributed amongst the nodes of a high-performance computing (HPC) cluster. Meshing operations within CDT3D utilize a speculative execution model, enabling the strict adaptation of subdomains' interior elements. Interface elements undergo several iterations of shifting so that they are adapted when their data dependencies are resolved. PREMA aids in this endeavor by providing asynchronous message passing between encapsulations of data, work load balancing, and migration capabilities all within a globally addressable namespace. PREMA also assists in establishing data dependencies between subdomains, thus enabling "neighborhoods" of subdomains to work independently of each other in performing interface shifts and adaptation. Preliminary results show that the presented method is able to produce meshes of comparable quality to those generated by the original shared memory CDT3D code. Given the costly overhead of collective communication seen by existing state-of-the-art software, relative communication performance of the presented distributed memory method also shows that its emphasis on avoiding global synchronization presents a potentially viable solution in achieving scalability when targeting large configurations of cores.
相關內容
The paper aims to address load imbalance caused by high in-degree distribution in graphs by applying the idea of rhizome to vertex-centric message-driven graph processing. Rhizome construction of the graph creates multiple named vertex address for any number of single large in-degree vertices. It then allows other vertices to point to any of the named addresses thus sharing the in-degree load. The rhizomes internally communicate and remain consistent to provide a unified and correct view of the vertex. Simulated experimental results show performance speed ups for BFS graph traversal on large chip sizes for the tested input graph datasets containing highly skewed in-degree distribution. The improvements come from sharing the in-degree compute workload among memory-processing elements and also lowering contention on the network-on-chip.
Text data augmentation is a complex problem due to the discrete nature of sentences. Although rule-based augmentation methods are widely adopted in real-world applications because of their simplicity, they suffer from potential semantic damage. Previous researchers have suggested easy data augmentation with soft labels (softEDA), employing label smoothing to mitigate this problem. However, finding the best factor for each model and dataset is challenging; therefore, using softEDA in real-world applications is still difficult. In this paper, we propose adapting AutoAugment to solve this problem. The experimental results suggest that the proposed method can boost existing augmentation methods and that rule-based methods can enhance cutting-edge pre-trained language models. We offer the source code.
This paper introduces a novel unsupervised technique that utilizes large language models (LLMs) to determine the most suitable dense retriever for a specific test(target) corpus. Selecting the appropriate dense retriever is vital for numerous IR applications that employ these retrievers, trained on public datasets, to encode or conduct searches within a new private target corpus. The effectiveness of a dense retriever can significantly diminish when applied to a target corpus that diverges in domain or task from the original training set. The problem becomes more pronounced in cases where the target corpus is unlabeled, e.g. in zero-shot scenarios, rendering direct evaluation of the model's effectiveness on the target corpus unattainable. Therefore, the unsupervised selection of an optimally pre-trained dense retriever, especially under conditions of domain shift, emerges as a critical challenge. Existing methodologies for ranking dense retrievers fall short in addressing these domain shift scenarios. To tackle this, our method capitalizes on LLMs to create pseudo-relevant queries, labels, and reference lists by analyzing a subset of documents from the target corpus. This allows for the ranking of dense retrievers based on their performance with these pseudo-relevant signals. Significantly, this strategy is the first to depend exclusively on the target corpus data, removing the necessity for training data and test labels. We assessed the effectiveness of our approach by compiling a comprehensive pool of cutting-edge dense retrievers and comparing our method against traditional dense retriever selection benchmarks. The findings reveal that our proposed solution surpasses the existing benchmarks in both the selection and ranking of dense retrievers.
Hand motion capture data is now relatively easy to obtain, even for complicated grasps; however this data is of limited use without the ability to retarget it onto the hands of a specific character or robot. The target hand may differ dramatically in geometry, number of degrees of freedom (DOFs), or number of fingers. We present a simple, but effective framework capable of kinematically retargeting multiple human hand-object manipulations from a publicly available dataset to a wide assortment of kinematically and morphologically diverse target hands through the exploitation of contact areas. We do so by formulating the retarget operation as a non-isometric shape matching problem and use a combination of both surface contact and marker data to progressively estimate, refine, and fit the final target hand trajectory using inverse kinematics (IK). Foundational to our framework is the introduction of a novel shape matching process, which we show enables predictable and robust transfer of contact data over full manipulations while providing an intuitive means for artists to specify correspondences with relatively few inputs. We validate our framework through thirty demonstrations across five different hand shapes and six motions of different objects. We additionally compare our method against existing hand retargeting approaches. Finally, we demonstrate our method enabling novel capabilities such as object substitution and the ability to visualize the impact of design choices over full trajectories.
We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this paper, we apply SLM to speech dialog applications where the dialog states are inferred directly from the audio signal. Task-oriented dialogs often contain domain-specific entities, i.e., restaurants, hotels, train stations, and city names, which are difficult to recognize, however, critical for the downstream applications. Inspired by the RAG (retrieval-augmented generation) paradigm, we propose a retrieval augmented SLM (ReSLM) that overcomes this weakness. We first train a speech retriever to retrieve text entities mentioned in the audio. The retrieved entities are then added as text inputs to the underlying SLM to bias model predictions. We evaluated ReSLM on speech MultiWoz task (DSTC-11 challenge), and found that this retrieval augmentation boosts model performance, achieving joint goal accuracy (38.6% vs 32.7%), slot error rate (20.6% vs 24.8%) and ASR word error rate (5.5% vs 6.7%). While demonstrated on dialog state tracking, our approach is broadly applicable to other speech tasks requiring contextual information or domain-specific entities, such as contextual ASR with biasing capability.
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities. In this paper, we survey recent advances and challenges in an issue-specific manner. We discuss three critical topics for task-oriented dialog systems: (1) improving data efficiency to facilitate dialog system modeling in low-resource settings, (2) modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance, and (3) integrating domain ontology knowledge into the dialog model in both pipeline and end-to-end models. We also review the recent progresses in dialog evaluation and some widely-used corpora. We believe that this survey can shed a light on future research in task-oriented dialog systems.
Representation learning on a knowledge graph (KG) is to embed entities and relations of a KG into low-dimensional continuous vector spaces. Early KG embedding methods only pay attention to structured information encoded in triples, which would cause limited performance due to the structure sparseness of KGs. Some recent attempts consider paths information to expand the structure of KGs but lack explainability in the process of obtaining the path representations. In this paper, we propose a novel Rule and Path-based Joint Embedding (RPJE) scheme, which takes full advantage of the explainability and accuracy of logic rules, the generalization of KG embedding as well as the supplementary semantic structure of paths. Specifically, logic rules of different lengths (the number of relations in rule body) in the form of Horn clauses are first mined from the KG and elaborately encoded for representation learning. Then, the rules of length 2 are applied to compose paths accurately while the rules of length 1 are explicitly employed to create semantic associations among relations and constrain relation embeddings. Besides, the confidence level of each rule is also considered in optimization to guarantee the availability of applying the rule to representation learning. Extensive experimental results illustrate that RPJE outperforms other state-of-the-art baselines on KG completion task, which also demonstrate the superiority of utilizing logic rules as well as paths for improving the accuracy and explainability of representation learning.
The design of deep graph models still remains to be investigated and the crucial part is how to explore and exploit the knowledge from different hops of neighbors in an efficient way. In this paper, we propose a novel RNN-like deep graph neural network architecture by incorporating AdaBoost into the computation of network; and the proposed graph convolutional network called AdaGCN~(AdaBoosting Graph Convolutional Network) has the ability to efficiently extract knowledge from high-order neighbors and integrate knowledge from different hops of neighbors into the network in an AdaBoost way. We also present the architectural difference between AdaGCN and existing graph convolutional methods to show the benefits of our proposal. Finally, extensive experiments demonstrate the state-of-the-art prediction performance and the computational advantage of our approach AdaGCN.
Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major challenges that hinder its application in embedded devices, low resolution output and heavy model weight. To this end, this paper presents an accurate yet compact deep network for efficient salient object detection. More specifically, given a coarse saliency prediction in the deepest layer, we first employ residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy. Secondly, we further propose reverse attention to guide such side-output residual learning in a top-down manner. By erasing the current predicted salient regions from side-output features, the network can eventually explore the missing object parts and details which results in high resolution and accuracy. Experiments on six benchmark datasets demonstrate that the proposed approach compares favorably against state-of-the-art methods, and with advantages in terms of simplicity, efficiency (45 FPS) and model size (81 MB).
This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence. We also propose a self-attention mechanism and a special regularization term for the model. As a side effect, the embedding comes with an easy way of visualizing what specific parts of the sentence are encoded into the embedding. We evaluate our model on 3 different tasks: author profiling, sentiment classification, and textual entailment. Results show that our model yields a significant performance gain compared to other sentence embedding methods in all of the 3 tasks.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191