No Arabic abstract
Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the same scale, i.e., all attention heads are in the same resolution, resulting in the limited power of the Transformer. To remedy this, we propose a novel and efficient structure named Adaptive Multi-Resolution Attention (AdaMRA for short), which scales linearly to sequence length in terms of time and space. Specifically, we leverage a multi-resolution multi-head attention mechanism, enabling attention heads to capture long-range contextual information in a coarse-to-fine fashion. Moreover, to capture the potential relations between query representation and clues of different attention granularities, we leave the decision of which resolution of attention to use to query, which further improves the models capacity compared to vanilla Transformer. In an effort to reduce complexity, we adopt kernel attention without degrading the performance. Extensive experiments on several benchmarks demonstrate the effectiveness and efficiency of our model by achieving a state-of-the-art performance-efficiency-memory trade-off. To facilitate AdaMRA utilization by the scientific community, the code implementation will be made publicly available.
Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences, as the standard self-attention mechanism of the Transformer uses $O(n^2)$ time and space with respect to sequence length. In this paper, we demonstrate that the self-attention mechanism can be approximated by a low-rank matrix. We further exploit this finding to propose a new self-attention mechanism, which reduces the overall self-attention complexity from $O(n^2)$ to $O(n)$ in both time and space. The resulting linear transformer, the textit{Linformer}, performs on par with standard Transformer models, while being much more memory- and time-efficient.
This paper describes an end-to-end solution for the relationship prediction task in heterogeneous, multi-relational graphs. We particularly address two building blocks in the pipeline, namely heterogeneous graph representation learning and negative sampling. Existing message passing-based graph neural networks use edges either for graph traversal and/or selection of message encoding functions. Ignoring the edge semantics could have severe repercussions on the quality of embeddings, especially when dealing with two nodes having multiple relations. Furthermore, the expressivity of the learned representation depends on the quality of negative samples used during training. Although existing hard negative sampling techniques can identify challenging negative relationships for optimization, new techniques are required to control false negatives during training as false negatives could corrupt the learning process. To address these issues, first, we propose RelGNN -- a message passing-based heterogeneous graph attention model. In particular, RelGNN generates the states of different relations and leverages them along with the node states to weigh the messages. RelGNN also adopts a self-attention mechanism to balance the importance of attribute features and topological features for generating the final entity embeddings. Second, we introduce a parameter-free negative sampling technique -- adaptive self-adversarial (ASA) negative sampling. ASA reduces the false-negative rate by leveraging positive relationships to effectively guide the identification of true negative samples. Our experimental evaluation demonstrates that RelGNN optimized by ASA for relationship prediction improves state-of-the-art performance across established benchmarks as well as on a real industrial dataset.
Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution inputs. To remedy this drawback, this paper proposes a novel efficient attention mechanism equivalent to dot-product attention but with substantially less memory and computational costs. Its resource efficiency allows more widespread and flexible integration of attention modules into a network, which leads to better accuracies. Empirical evaluations demonstrated the effectiveness of its advantages. Efficient attention modules brought significant performance boosts to object detectors and instance segmenters on MS-COCO 2017. Further, the resource efficiency democratizes attention to complex models, where high costs prohibit the use of dot-product attention. As an exemplar, a model with efficient attention achieved state-of-the-art accuracies for stereo depth estimation on the Scene Flow dataset. Code is available at https://github.com/cmsflash/efficient-attention.
Detecting and mapping informal settlements encompasses several of the United Nations sustainable development goals. This is because informal settlements are home to the most socially and economically vulnerable people on the planet. Thus, understanding where these settlements are is of paramount importance to both government and non-government organizations (NGOs), such as the United Nations Childrens Fund (UNICEF), who can use this information to deliver effective social and economic aid. We propose two effective methods for detecting and mapping the locations of informal settlements. One uses only low-resolution (LR), freely available, Sentinel-2 multispectral satellite imagery with noisy annotations, whilst the other is a deep learning approach that uses only costly very-high-resolution (VHR) satellite imagery. To our knowledge, we are the first to map informal settlements successfully with low-resolution satellite imagery. We extensively evaluate and compare the proposed methods. Please find additional material at https://frontierdevelopmentlab.github.io/informal-settlements/.
Data scarcity is a tremendous challenge in causal effect estimation. In this paper, we propose to exploit additional data sources to facilitate estimating causal effects in the target population. Specifically, we leverage additional source datasets which share similar causal mechanisms with the target observations to help infer causal effects of the target population. We propose three levels of knowledge transfer, through modelling the outcomes, treatments, and confounders. To achieve consistent positive transfer, we introduce learnable parametric transfer factors to adaptively control the transfer strength, and thus achieving a fair and balanced knowledge transfer between the sources and the target. The proposed method can infer causal effects in the target population without prior knowledge of data discrepancy between the additional data sources and the target. Experiments on both synthetic and real-world datasets show the effectiveness of the proposed method as compared with recent baselines.