There is increasing adoption of artificial intelligence in drug discovery. However, existing works use machine learning to mainly utilize the chemical structures of molecules yet ignore the vast textual knowledge available in chemistry. Incorporating textual knowledge enables us to realize new drug design objectives, adapt to text-based instructions, and predict complex biological activities. We present a multi-modal molecule structure-text model, MoleculeSTM, by jointly learning molecule's chemical structures and textual descriptions via a contrastive learning strategy. To train MoleculeSTM, we construct the largest multi-modal dataset to date, namely PubChemSTM, with over 280K chemical structure-text pairs. To demonstrate the effectiveness and utility of MoleculeSTM, we design two challenging zero-shot tasks based on text instructions, including structure-text retrieval and molecule editing. MoleculeSTM possesses two main properties: open vocabulary and compositionality via natural language. In experiments, MoleculeSTM obtains the state-of-the-art generalization ability to novel biochemical concepts across various benchmarks.

大型变压器模型在各种自然语言处理（NLP）任务上显示出令人鼓舞的性能。尽管AI社区已将模型量表扩展到了万亿个参数级别，但由于延迟，吞吐量和内存约束，仍不确定100亿参数模型的实际部署。在本文中，我们提出了Energonai，以解决单个或多GPU系统上有效部署1000亿参数变压器模型的挑战。 Energonai采用层次结构控制器系统体系结构来协调多个设备并有效支持不同的并行模式。它将子模型的执行委托给单个控制器样式的多个工人，并以多控制器样式的工人之间的工人之间的张量并行性和管道并行性。在新的架构上，我们提出了三种技术，即非阻滞管道并行性，分布式冗余计算消除和同行记忆池。 Energonai使用户能够编程复杂的并行代码与串行编码相同。与FertransFormer相比，我们已经证明，Energonai在延迟和吞吐量方面具有较高的性能。在我们的实验中，Energonai可以在张量并行性，管道并行性的10％可伸缩性中实现37％的潜伏期降低，并通过使用较大的异质记忆空间以有限的性能降低的成本来提高对单个GPU推断的模型量表。

现在，我们目睹了深度学习方法在各种蛋白质（或数据集）中的重大进展。但是，缺乏评估不同方法的性能的标准基准，这阻碍了该领域的深度学习进步。在本文中，我们提出了一种称为PEER的基准，这是一种用于蛋白质序列理解的全面和多任务基准。 PEER提供了一组不同的蛋白质理解任务，包括蛋白质功能预测，蛋白质定位预测，蛋白质结构预测，蛋白质 - 蛋白质相互作用预测和蛋白质 - 配体相互作用预测。我们评估每个任务的不同类型的基于序列的方法，包括传统的特征工程方法，不同的序列编码方法以及大规模的预训练蛋白质语言模型。此外，我们还研究了这些方法在多任务学习设置下的性能。实验结果表明，大规模的预训练蛋白质语言模型可实现大多数单个任务的最佳性能，共同训练多个任务进一步提高了性能。该基准的数据集和源代码均可在https://github.com/deepgraphlearning/peer_benchmark上获得

Graph Neural Networks (GNNs), originally proposed for node classification, have also motivated many recent works on edge prediction (a.k.a., link prediction). However, existing methods lack elaborate design regarding the distinctions between two tasks that have been frequently overlooked: (i) edges only constitute the topology in the node classification task but can be used as both the topology and the supervisions (i.e., labels) in the edge prediction task; (ii) the node classification makes prediction over each individual node, while the edge prediction is determinated by each pair of nodes. To this end, we propose a novel edge prediction paradigm named Edge-aware Message PassIng neuRal nEtworks (EMPIRE). Concretely, we first introduce an edge splitting technique to specify use of each edge where each edge is solely used as either the topology or the supervision (named as topology edge or supervision edge). We then develop a new message passing mechanism that generates the messages to source nodes (through topology edges) being aware of target nodes (through supervision edges). In order to emphasize the differences between pairs connected by supervision edges and pairs unconnected, we further weight the messages to highlight the relative ones that can reflect the differences. In addition, we design a novel negative node-pair sampling trick that efficiently samples 'hard' negative instances in the supervision instances, and can significantly improve the performance. Experimental results verify that the proposed method can significantly outperform existing state-of-the-art models regarding the edge prediction task on multiple homogeneous and heterogeneous graph datasets.

We present the Group Propagation Vision Transformer (GPViT): a novel nonhierarchical (i.e. non-pyramidal) transformer model designed for general visual recognition with high-resolution features. High-resolution features (or tokens) are a natural fit for tasks that involve perceiving fine-grained details such as detection and segmentation, but exchanging global information between these features is expensive in memory and computation because of the way self-attention scales. We provide a highly efficient alternative Group Propagation Block (GP Block) to exchange global information. In each GP Block, features are first grouped together by a fixed number of learnable group tokens; we then perform Group Propagation where global information is exchanged between the grouped features; finally, global information in the updated grouped features is returned back to the image features through a transformer decoder. We evaluate GPViT on a variety of visual recognition tasks including image classification, semantic segmentation, object detection, and instance segmentation. Our method achieves significant performance gains over previous works across all tasks, especially on tasks that require high-resolution outputs, for example, our GPViT-L3 outperforms Swin Transformer-B by 2.0 mIoU on ADE20K semantic segmentation with only half as many parameters. Code and pre-trained models are available at https://github.com/ChenhongyiYang/GPViT .

In recent years, the number of parameters of one deep learning (DL) model has been growing much faster than the growth of GPU memory space. People who are inaccessible to a large number of GPUs resort to heterogeneous training systems for storing model parameters in CPU memory. Existing heterogeneous systems are based on parallelization plans in the scope of the whole model. They apply a consistent parallel training method for all the operators in the computation. Therefore, engineers need to pay a huge effort to incorporate a new type of model parallelism and patch its compatibility with other parallelisms. For example, Mixture-of-Experts (MoE) is still incompatible with ZeRO-3 in Deepspeed. Also, current systems face efficiency problems on small scale, since they are designed and tuned for large-scale training. In this paper, we propose Elixir, a new parallel heterogeneous training system, which is designed for efficiency and flexibility. Elixir utilizes memory resources and computing resources of both GPU and CPU. For flexibility, Elixir generates parallelization plans in the granularity of operators. Any new type of model parallelism can be incorporated by assigning a parallel pattern to the operator. For efficiency, Elixir implements a hierarchical distributed memory management scheme to accelerate inter-GPU communications and CPU-GPU data transmissions. As a result, Elixir can train a 30B OPT model on an A100 with 40GB CUDA memory, meanwhile reaching 84% efficiency of Pytorch GPU training. With its super-linear scalability, the training efficiency becomes the same as Pytorch GPU training on multiple GPUs. Also, large MoE models can be trained 5.3x faster than dense models of the same size. Now Elixir is integrated into ColossalAI and is available on its main branch.

Node classification for graph-structured data aims to classify nodes whose labels are unknown. While studies on static graphs are prevalent, few studies have focused on dynamic graph node classification. Node classification on dynamic graphs is challenging for two reasons. First, the model needs to capture both structural and temporal information, particularly on dynamic graphs with a long history and require large receptive fields. Second, model scalability becomes a significant concern as the size of the dynamic graph increases. To address these problems, we propose the Time Augmented Dynamic Graph Neural Network (TADGNN) framework. TADGNN consists of two modules: 1) a time augmentation module that captures the temporal evolution of nodes across time structurally, creating a time-augmented spatio-temporal graph, and 2) an information propagation module that learns the dynamic representations for each node across time using the constructed time-augmented graph. We perform node classification experiments on four dynamic graph benchmarks. Experimental results demonstrate that TADGNN framework outperforms several static and dynamic state-of-the-art (SOTA) GNN models while demonstrating superior scalability. We also conduct theoretical and empirical analyses to validate the efficiency of the proposed method. Our code is available at https://sites.google.com/view/tadgnn.

Automated identification of myocardial scar from late gadolinium enhancement cardiac magnetic resonance images (LGE-CMR) is limited by image noise and artifacts such as those related to motion and partial volume effect. This paper presents a novel joint deep learning (JDL) framework that improves such tasks by utilizing simultaneously learned myocardium segmentations to eliminate negative effects from non-region-of-interest areas. In contrast to previous approaches treating scar detection and myocardium segmentation as separate or parallel tasks, our proposed method introduces a message passing module where the information of myocardium segmentation is directly passed to guide scar detectors. This newly designed network will efficiently exploit joint information from the two related tasks and use all available sources of myocardium segmentation to benefit scar identification. We demonstrate the effectiveness of JDL on LGE-CMR images for automated left ventricular (LV) scar detection, with great potential to improve risk prediction in patients with both ischemic and non-ischemic heart disease and to improve response rates to cardiac resynchronization therapy (CRT) for heart failure patients. Experimental results show that our proposed approach outperforms multiple state-of-the-art methods, including commonly used two-step segmentation-classification networks, and multitask learning schemes where subtasks are indirectly interacted.

The selection of an optimal pacing site, which is ideally scar-free and late activated, is critical to the response of cardiac resynchronization therapy (CRT). Despite the success of current approaches formulating the detection of such late mechanical activation (LMA) regions as a problem of activation time regression, their accuracy remains unsatisfactory, particularly in cases where myocardial scar exists. To address this issue, this paper introduces a multi-task deep learning framework that simultaneously estimates LMA amount and classify the scar-free LMA regions based on cine displacement encoding with stimulated echoes (DENSE) magnetic resonance imaging (MRI). With a newly introduced auxiliary LMA region classification sub-network, our proposed model shows more robustness to the complex pattern cause by myocardial scar, significantly eliminates their negative effects in LMA detection, and in turn improves the performance of scar classification. To evaluate the effectiveness of our method, we tests our model on real cardiac MR images and compare the predicted LMA with the state-of-the-art approaches. It shows that our approach achieves substantially increased accuracy. In addition, we employ the gradient-weighted class activation mapping (Grad-CAM) to visualize the feature maps learned by all methods. Experimental results suggest that our proposed model better recognizes the LMA region pattern.

自主导航的同时本地化和映射（SLAM）框架依赖于强大的数据关联来识别循环封闭以进行后端轨迹优化。对于配备了多层回声器（MBE）的自动水下车辆（AUV），由于海床中可识别的地标的稀缺性，数据关联尤其具有挑战性MBE数据的低分辨率特征。循环封闭检测的深度学习解决方案已显示出来自更结构化环境的数据的出色性能。但是，它们转移到海底领域并不是直接的，并且由于缺乏测深的数据集而阻碍了移植它们的努力。因此，在本文中，我们提出了一种神经网络体系结构，旨在展示将这种技术适应测深数据中对应匹配的潜力。我们从AUV任务中训练我们的框架，并评估其在循环闭合检测任务和粗点云对齐任务上的性能。最后，我们在更传统的方法上展示了其潜力，并释放其实现和所使用的数据集。