اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدETC: Encoding Long and Structured Inputs in Transformers
73
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended Transformer Construction (ETC), that addresses two key challenges of standard Transformer architectures, namely scaling input length and encoding structured inputs. To scale attention to longer inputs, we introduce a novel global-local attention mechanism between global tokens and regular input tokens. We also show that combining global-local attention with relative position encodings and a Contrastive Predictive Coding (CPC) pre-training objective allows ETC to encode structured inputs. We achieve state-of-the-art results on four natural language datasets requiring long and/or structured inputs.
قيم البحث
اقرأ أيضاً
We show that viewing graphs as sets of node features and incorporating structural and positional information into a transformer architecture is able to outperform representations learned with classical graph neural networks (GNNs). Our model, GraphiT
, encodes such information by (i) leveraging relative positional encoding strategies in self-attention scores based on positive definite kernels on graphs, and (ii) enumerating and encoding local sub-structures such as paths of short length. We thoroughly evaluate these two ideas on many classification and regression tasks, demonstrating the effectiveness of each of them independently, as well as their combination. In addition to performing well on standard benchmarks, our model also admits natural visualization mechanisms for interpreting graph motifs explaining the predictions, making it a potentially strong candidate for scientific applications where interpretation is important. Code available at https://github.com/inria-thoth/GraphiT.
The recently-proposed Perceiver model obtains good results on several domains (images, audio, multimodal, point clouds) while scaling linearly in compute and memory with the input size. While the Perceiver supports many kinds of inputs, it can only p
roduce very simple outputs such as class scores. Perceiver IO overcomes this limitation without sacrificing the originals appealing properties by learning to flexibly query the models latent space to produce outputs of arbitrary size and semantics. Perceiver IO still decouples model depth from data size and still scales linearly with data size, but now with respect to both input and output sizes. The full Perceiver IO model achieves strong results on tasks with highly structured output spaces, such as natural language and visual understanding, StarCraft II, and multi-task and multi-modal domains. As highlights, Perceiver IO matches a Transformer-based BERT baseline on the GLUE language benchmark without the need for input tokenization and achieves state-of-the-art performance on Sintel optical flow estimation.
Tree-based ensemble methods, as Random Forests and Gradient Boosted Trees, have been successfully used for regression in many applications and research studies. Furthermore, these methods have been extended in order to deal with uncertainty in the ou
tput variable, using for example a quantile loss in Random Forests (Meinshausen, 2006). To the best of our knowledge, no extension has been provided yet for dealing with uncertainties in the input variables, even though such uncertainties are common in practical situations. We propose here such an extension by showing how standard regression trees optimizing a quadratic loss can be adapted and learned while taking into account the uncertainties in the inputs. By doing so, one no longer assumes that an observation lies into a single region of the regression tree, but rather that it belongs to each region with a certain probability. Experiments conducted on several data sets illustrate the good behavior of the proposed extension.
When manipulating three-dimensional data, it is possible to ensure that rotational and translational symmetries are respected by applying so-called SE(3)-equivariant models. Protein structure prediction is a prominent example of a task which displays
these symmetries. Recent work in this area has successfully made use of an SE(3)-equivariant model, applying an iterative SE(3)-equivariant attention mechanism. Motivated by this application, we implement an iterative version of the SE(3)-Transformer, an SE(3)-equivariant attention-based model for graph data. We address the additional complications which arise when applying the SE(3)-Transformer in an iterative fashion, compare the iterative and single-pa
Inspired by the fruit-fly olfactory circuit, the Fly Bloom Filter [Dasgupta et al., 2018] is able to efficiently summarize the data with a single pass and has been used for novelty detection. We propose a new classifier (for binary and multi-class cl
assification) that effectively encodes the different local neighborhoods for each class with a per-class Fly Bloom Filter. The inference on test data requires an efficient {tt FlyHash} [Dasgupta, et al., 2017] operation followed by a high-dimensional, but {em sparse}, dot product with the per-class Bloom Filters. The learning is trivially parallelizable. On the theoretical side, we establish conditions under which the prediction of our proposed classifier on any test example agrees with the prediction of the nearest neighbor classifier with high probability. We extensively evaluate our proposed scheme with over $50$ data sets of varied data dimensionality to demonstrate that the predictive performance of our proposed neuroscience inspired classifier is competitive the the nearest-neighbor classifiers and other single-pass classifiers.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
