The accurate prediction of changes in protein stability under multiple amino acid substitutions is essential for realising true in-silico protein re-design. To this purpose, we propose improvements to state-of-the-art Deep learning (DL) protein stability prediction models, enabling first-of-a-kind predictions for variable numbers of amino acid substitutions, on structural representations, by decoupling the atomic and residue scales of protein representations. This was achieved using E(3)-equivariant graph neural networks (EGNNs) for both atomic environment (AE) embedding and residue-level scoring tasks. Our AE embedder was used to featurise a residue-level graph, then trained to score mutant stability ( G). To achieve effective training of this predictive EGNN we have leveraged the unprecedented scale of a new high-throughput protein stability experimental dataset, Mega-scale. Finally, we demonstrate the immediately promising results of this procedure, discuss the current shortcomings, and highlight potential future strategies. Protein stability is a crucial component of protein evolution (Godoy-Ruiz et al., 2004), it lies at the root of our understanding of many human diseases (Peng & Alexov, 2016) and plays a major role in protein design and engineering (Qing et al., 2022).

This paper presents an efficient hardware implementation of the recently proposed Optimized Deep Event-driven Spiking Neural Network Architecture (ODESA). ODESA is the first network to have end-to-end multi-layer online local supervised training without using gradients and has the combined adaptation of weights and thresholds in an efficient hierarchical structure. This research shows that the network architecture and the online training of weights and thresholds can be implemented efficiently on a large scale in hardware. The implementation consists of a multi-layer Spiking Neural Network (SNN) and individual training modules for each layer that enable online self-learning without using back-propagation. By using simple local adaptive selection thresholds, a Winner-Takes-All (WTA) constraint on each layer, and a modified weight update rule that is more amenable to hardware, the trainer module allocates neuronal resources optimally at each layer without having to pass high-precision error measurements across layers. All elements in the system, including the training module, interact using event-based binary spikes. The hardware-optimized implementation is shown to preserve the performance of the original algorithm across multiple spatial-temporal classification problems with significantly reduced hardware requirements.

A number of recent benchmarks seek to assess how well models handle natural language negation. However, these benchmarks lack the controlled example paradigms that would allow us to infer whether a model had learned how negation morphemes semantically scope. To fill these analytical gaps, we present the Scoped Negation NLI (ScoNe-NLI) benchmark, which contains contrast sets of six examples with up to two negations where either zero, one, or both negative morphemes affect the NLI label. We use ScoNe-NLI to assess fine-tuning and in-context learning strategies. We find that RoBERTa and DeBERTa models solve ScoNe-NLI after many shot fine-tuning. For in-context learning, we test InstructGPT models and find that most prompt strategies are not successful, including those using step-by-step reasoning. To better understand this result, we extend ScoNe with ScoNe-NLG, a sentence completion test set that embeds negation reasoning in short narratives. Here, InstructGPT is successful, which reveals the model can correctly reason about negation, but struggles to do so on prompt-adapted NLI examples outside of its core pretraining regime.

This paper reveals a new appeal of the recently emerged large-kernel Convolutional Neural Networks (ConvNets): as the teacher in Knowledge Distillation (KD) for small-kernel ConvNets. While Transformers have led state-of-the-art (SOTA) performance in various fields with ever-larger models and labeled data, small-kernel ConvNets are considered more suitable for resource-limited applications due to the efficient convolution operation and compact weight sharing. KD is widely used to boost the performance of small-kernel ConvNets. However, previous research shows that it is not quite effective to distill knowledge (e.g., global information) from Transformers to small-kernel ConvNets, presumably due to their disparate architectures. We hereby carry out a first-of-its-kind study unveiling that modern large-kernel ConvNets, a compelling competitor to Vision Transformers, are remarkably more effective teachers for small-kernel ConvNets, due to more similar architectures. Our findings are backed up by extensive experiments on both logit-level and feature-level KD ``out of the box", with no dedicated architectural nor training recipe modifications. Notably, we obtain the \textbf{best-ever pure ConvNet} under 30M parameters with \textbf{83.1\%} top-1 accuracy on ImageNet, outperforming current SOTA methods including ConvNeXt V2 and Swin V2. We also find that beneficial characteristics of large-kernel ConvNets, e.g., larger effective receptive fields, can be seamlessly transferred to students through this large-to-small kernel distillation. Code is available at: \url{https://github.com/VITA-Group/SLaK}.

Humans leverage compositionality to efficiently learn new concepts, understanding how familiar parts can combine together to form novel objects. In contrast, popular computer vision models struggle to make the same types of inferences, requiring more data and generalizing less flexibly than people do. Here, we study these distinctively human abilities across a range of different types of visual composition, examining how people classify and generate ``alien figures'' with rich relational structure. We also develop a Bayesian program induction model which searches for the best programs for generating the candidate visual figures, utilizing a large program space containing different compositional mechanisms and abstractions. In few shot classification tasks, we find that people and the program induction model can make a range of meaningful compositional generalizations, with the model providing a strong account of the experimental data as well as interpretable parameters that reveal human assumptions about the factors invariant to category membership (here, to rotation and changing part attachment). In few shot generation tasks, both people and the models are able to construct compelling novel examples, with people behaving in additional structured ways beyond the model capabilities, e.g. making choices that complete a set or reconfiguring existing parts in highly novel ways. To capture these additional behavioral patterns, we develop an alternative model based on neuro-symbolic program induction: this model also composes new concepts from existing parts yet, distinctively, it utilizes neural network modules to successfully capture residual statistical structure. Together, our behavioral and computational findings show how people and models can produce a rich variety of compositional behavior when classifying and generating visual objects.

The projection operation is a critical component in a wide range of optimization algorithms, such as online gradient descent (OGD), for enforcing constraints and achieving optimal regret bounds. However, it suffers from computational complexity limitations in high-dimensional settings or when dealing with ill-conditioned constraint sets. Projection-free algorithms address this issue by replacing the projection oracle with more efficient optimization subroutines. But to date, these methods have been developed primarily in the Euclidean setting, and while there has been growing interest in optimization on Riemannian manifolds, there has been essentially no work in trying to utilize projection-free tools here. An apparent issue is that non-trivial affine functions are generally non-convex in such domains. In this paper, we present methods for obtaining sub-linear regret guarantees in online geodesically convex optimization on curved spaces for two scenarios: when we have access to (a) a separation oracle or (b) a linear optimization oracle. For geodesically convex losses, and when a separation oracle is available, our algorithms achieve $O(T^{1/2}\:)$ and $O(T^{3/4}\;)$ adaptive regret guarantees in the full information setting and the bandit setting, respectively. When a linear optimization oracle is available, we obtain regret rates of $O(T^{3/4}\;)$ for geodesically convex losses and $O(T^{2/3}\; log T )$ for strongly geodesically convex losses

Text classification in education, usually called auto-tagging, is the automated process of assigning relevant tags to educational content, such as questions and textbooks. However, auto-tagging suffers from a data scarcity problem, which stems from two major challenges: 1) it possesses a large tag space and 2) it is multi-label. Though a retrieval approach is reportedly good at low-resource scenarios, there have been fewer efforts to directly address the data scarcity problem. To mitigate these issues, here we propose a novel retrieval approach CEAA that provides effective learning in educational text classification. Our main contributions are as follows: 1) we leverage transfer learning from question-answering datasets, and 2) we propose a simple but effective data augmentation method introducing cross-encoder style texts to a bi-encoder architecture for more efficient inference. An extensive set of experiments shows that our proposed method is effective in multi-label scenarios and low-resource tags compared to state-of-the-art models.

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and latency while preserving model accuracy, it remains unclear whether we can leverage INT4 (which doubles peak hardware throughput) to achieve further latency improvement. In this study, we explore the feasibility of employing INT4 weight and activation (W4A4) quantization for language models. Our findings indicate that W4A4 quantization introduces no to negligible accuracy degradation for encoder-only and encoder-decoder models, but causes a significant accuracy drop for decoder-only models. To materialize the performance gain using W4A4, we develop a highly optimized end-to-end W4A4 encoder inference pipeline supporting different quantization strategies. Our INT4 pipeline is $8.5\times$ faster for latency-oriented scenarios and up to $3\times$ for throughput-oriented scenarios compared to the inference of FP16, and improves the SOTA BERT INT8 performance from FasterTransformer by up to $1.7\times$. We provide insights into the failure cases when applying W4A4 to decoder-only models, and further explore the compatibility of INT4 quantization with other compression methods, like pruning and layer reduction.

We study a class of distributed optimization algorithms that aim to alleviate high communication costs by allowing the clients to perform multiple local gradient-type training steps prior to communication. While methods of this type have been studied for about a decade, the empirically observed acceleration properties of local training eluded all attempts at theoretical understanding. In a recent breakthrough, Mishchenko et al. (ICML 2022) proved that local training, when properly executed, leads to provable communication acceleration, and this holds in the strongly convex regime without relying on any data similarity assumptions. However, their method ProxSkip requires all clients to take the same number of local training steps in each communication round. Inspired by a common sense intuition, we start our investigation by conjecturing that clients with ``less important'' data should be able to get away with fewer local training steps without this impacting the overall communication complexity of the method. It turns out that this intuition is correct: we managed to redesign the original ProxSkip method to achieve this. In particular, we prove that our modified method, for which coin the name GradSkip, converges linearly under the same assumptions, has the same accelerated communication complexity, while the number of local gradient steps can be reduced relative to a local condition number. We further generalize our method by extending the randomness of probabilistic alternations to arbitrary unbiased compression operators and considering a generic proximable regularizer. This generalization, which we call GradSkip+, recovers several related methods in the literature as special cases. Finally, we present an empirical study on carefully designed toy problems that confirm our theoretical claims.

Training long-horizon robotic policies in complex physical environments is essential for many applications, such as robotic manipulation. However, learning a policy that can generalize to unseen tasks is challenging. In this work, we propose to achieve one-shot task generalization by decoupling plan generation and plan execution. Specifically, our method solves complex long-horizon tasks in three steps: build a paired abstract environment by simplifying geometry and physics, generate abstract trajectories, and solve the original task by an abstract-to-executable trajectory translator. In the abstract environment, complex dynamics such as physical manipulation are removed, making abstract trajectories easier to generate. However, this introduces a large domain gap between abstract trajectories and the actual executed trajectories as abstract trajectories lack low-level details and are not aligned frame-to-frame with the executed trajectory. In a manner reminiscent of language translation, our approach leverages a seq-to-seq model to overcome the large domain gap between the abstract and executable trajectories, enabling the low-level policy to follow the abstract trajectory. Experimental results on various unseen long-horizon tasks with different robot embodiments demonstrate the practicability of our methods to achieve one-shot task generalization.