Dan Busbridge

Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin et al. · apple-ml, meta-ai

Training stability is of great importance to Transformers. In this work, we investigate the training dynamics of Transformers by examining the evolution of the attention layers. In particular, we track the attention entropy for each attention head during the course of training, which is a proxy for model sharpness. We identify a common pattern across different architectures and tasks, where low attention entropy is accompanied by high training instability, which can take the form of oscillating loss or divergence. We denote the pathologically low attention entropy, corresponding to highly concentrated attention scores, as $\textit{entropy collapse}$. As a remedy, we propose $σ$Reparam, a simple and efficient solution where we reparametrize all linear layers with spectral normalization and an additional learned scalar. We demonstrate that $σ$Reparam successfully prevents entropy collapse in the attention layers, promoting more stable training. Additionally, we prove a tight lower bound of the attention entropy, which decreases exponentially fast with the spectral norm of the attention logits, providing additional motivation for our approach. We conduct experiments with $σ$Reparam on image classification, image self-supervised learning, machine translation, speech recognition, and language modeling tasks. We show that $σ$Reparam provides stability and robustness with respect to the choice of hyperparameters, going so far as enabling training (a) a Vision Transformer {to competitive performance} without warmup, weight decay, layer normalization or adaptive optimizers; (b) deep architectures in machine translation and (c) speech recognition to competitive performance without warmup and adaptive optimizers. Code is available at \url{https://github.com/apple/ml-sigma-reparam}.

Jason Ramapuram, Federico Danieli, Eeshan Dhekane et al. · apple-ml, berkeley

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between keys and queries. Recent work has explored alternatives to softmax attention in transformers, such as ReLU and sigmoid activations. In this work, we revisit sigmoid attention and conduct an in-depth theoretical and empirical analysis. Theoretically, we prove that transformers with sigmoid attention are universal function approximators and benefit from improved regularity compared to softmax attention. Through detailed empirical analysis, we identify stabilization of large initial attention norms during the early stages of training as a crucial factor for the successful training of models with sigmoid attention, outperforming prior attempts. We also introduce FLASHSIGMOID, a hardware-aware and memory-efficient implementation of sigmoid attention yielding a 17% inference kernel speed-up over FLASHATTENTION2 on H100 GPUs. Experiments across language, vision, and speech show that properly normalized sigmoid attention matches the strong performance of softmax attention on a wide range of domains and scales, which previous attempts at sigmoid attention were unable to fully achieve. Our work unifies prior art and establishes best practices for sigmoid attention as a drop-in softmax replacement in transformers.

Dan Busbridge, Jason Ramapuram, Pierre Ablin et al. · apple-ml, berkeley

Preserving training dynamics across batch sizes is an important tool for practical machine learning as it enables the trade-off between batch size and wall-clock time. This trade-off is typically enabled by a scaling rule, for example, in stochastic gradient descent, one should scale the learning rate linearly with the batch size. Another important machine learning tool is the model EMA, a functional copy of a target model, whose parameters move towards those of its target model according to an Exponential Moving Average (EMA) at a rate parameterized by a momentum hyperparameter. This model EMA can improve the robustness and generalization of supervised learning, stabilize pseudo-labeling, and provide a learning signal for Self-Supervised Learning (SSL). Prior works have not considered the optimization of the model EMA when performing scaling, leading to different training dynamics across batch sizes and lower model performance. In this work, we provide a scaling rule for optimization in the presence of a model EMA and demonstrate the rule's validity across a range of architectures, optimizers, and data modalities. We also show the rule's validity where the model EMA contributes to the optimization of the target model, enabling us to train EMA-based pseudo-labeling and SSL methods at small and large batch sizes. For SSL, we enable training of BYOL up to batch size 24,576 without sacrificing performance, a 6$\times$ wall-clock time reduction under idealized hardware settings.

Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram et al. · apple-ml

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing this representational capacity effectively requires a large amount of data, strong regularization, or both, to mitigate overfitting. Recently, the power of the Transformer has been unlocked by self-supervised pretraining strategies based on masked autoencoders which rely on reconstructing masked inputs, directly, or contrastively from unmasked content. This pretraining strategy which has been used in BERT models in NLP, Wav2Vec models in Speech and, recently, in MAE models in Vision, forces the model to learn about relationships between the content in different parts of the input using autoencoding related objectives. In this paper, we propose a novel, but surprisingly simple alternative to content reconstruction~-- that of predicting locations from content, without providing positional information for it. Doing so requires the Transformer to understand the positional relationships between different parts of the input, from their content alone. This amounts to an efficient implementation where the pretext task is a classification problem among all possible positions for each input token. We experiment on both Vision and Speech benchmarks, where our approach brings improvements over strong supervised training baselines and is comparable to modern unsupervised/self-supervised pretraining methods. Our method also enables Transformers trained without position embeddings to outperform ones trained with full position information.

Borja Rodríguez-Gálvez, Arno Blaas, Pau Rodríguez et al. · apple-ml

The mechanisms behind the success of multi-view self-supervised learning (MVSSL) are not yet fully understood. Contrastive MVSSL methods have been studied through the lens of InfoNCE, a lower bound of the Mutual Information (MI). However, the relation between other MVSSL methods and MI remains unclear. We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens. Through this ER bound, we show that clustering-based methods such as DeepCluster and SwAV maximize the MI. We also re-interpret the mechanisms of distillation-based approaches such as BYOL and DINO, showing that they explicitly maximize the reconstruction term and implicitly encourage a stable entropy, and we confirm this empirically. We show that replacing the objectives of common MVSSL methods with this ER bound achieves competitive performance, while making them stable when training with smaller batch sizes or smaller exponential moving average (EMA) coefficients. Github repo: https://github.com/apple/ml-entropy-reconstruction.

Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec et al. · apple-ml, berkeley

Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and fine-tuning a base unimodal model for bimodal generation. Diverging from previous approaches, we introduce the first tri-modal masked diffusion model pretrained from scratch on text, image-text, and audio-text data. We systematically analyze multimodal scaling laws, modality mixing ratios, noise schedules, and batch-size effects, and we provide optimized inference sampling defaults. Our batch-size analysis yields a novel stochastic differential equation (SDE)-based reparameterization that eliminates the need for tuning the optimal batch size as reported in recent work. This reparameterization decouples the physical batch size, often chosen based on compute constraints (GPU saturation, FLOP efficiency, wall-clock time), from the logical batch size, chosen to balance gradient variance during stochastic optimization. Finally, we pretrain a preliminary 3B-parameter tri-modal model on 6.4T tokens, demonstrating the capabilities of a unified design and achieving strong results in text generation, text-to-image tasks, and text-to-speech tasks. Our work represents the largest-scale systematic open study of multimodal discrete diffusion models conducted to date, providing insights into scaling behaviors across multiple modalities.

Andrius Ovsianas, Jason Ramapuram, Dan Busbridge et al. · apple-ml, berkeley

Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks. However, in numerous realistic scenarios, the downstream task might be biased with respect to the target label distribution. This in turn moves the learned fine-tuned model posterior away from the initial (label) bias-free self-supervised model posterior. In this work, we re-interpret SSL fine-tuning under the lens of Bayesian continual learning and consider regularization through the Elastic Weight Consolidation (EWC) framework. We demonstrate that self-regularization against an initial SSL backbone improves worst sub-group performance in Waterbirds by 5% and Celeb-A by 2% when using the ViT-B/16 architecture. Furthermore, to help simplify the use of EWC with SSL, we pre-compute and publicly release the Fisher Information Matrix (FIM), evaluated with 10,000 ImageNet-1K variates evaluated on large modern SSL architectures including ViT-B/16 and ResNet50 trained with DINO.

Skyler Seto, Barry-John Theobald, Federico Danieli et al.

Fully-test-time adaptation (F-TTA) can mitigate performance loss due to distribution shifts between train and test data (1) without access to the training data, and (2) without knowledge of the model training procedure. In online F-TTA, a pre-trained model is adapted using a stream of test samples by minimizing a self-supervised objective, such as entropy minimization. However, models adapted with online using entropy minimization, are unstable especially in single sample settings, leading to degenerate solutions, and limiting the adoption of TTA inference strategies. Prior works identify noisy, or unreliable, samples as a cause of failure in online F-TTA. One solution is to ignore these samples, which can lead to bias in the update procedure, slow adaptation, and poor generalization. In this work, we present a general framework for improving robustness of F-TTA to these noisy samples, inspired by self-paced learning and robust loss functions. Our proposed approach, Robust Entropy Adaptive Loss Minimization (REALM), achieves better adaptation accuracy than previous approaches throughout the adaptation process on corruptions of CIFAR-10 and ImageNet-1K, demonstrating its effectiveness.

Xavier Suau, Federico Danieli, T. Anderson Keller et al.

Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm performance for specific downstream tasks that require such information. We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data. DUET representations maintain information about an input transformation, while remaining semantically expressive. Compared to SimCLR (Chen et al., 2020) (unstructured and invariant) and ESSL (Dangovski et al., 2022) (unstructured and equivariant), the structured and equivariant nature of DUET representations enables controlled generation with lower reconstruction error, while controllability is not possible with SimCLR or ESSL. DUET also achieves higher accuracy for several discriminative tasks, and improves transfer learning.

Bruno Mlodozeniec, Pierre Ablin, Louis Béthune et al.

Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as $μ$P, have enabled transfer of optimal global hyperparameters across model sizes. These works propose an empirical practice of search for optimal global base hyperparameters at a small model size, and transfer to a large size. We extend these works in two key ways. To handle scaling along most important scaling axes, we propose the Complete$^{(d)}$ Parameterisation that unifies scaling in width and depth -- using an adaptation of CompleteP -- as well as in batch-size and training duration. Secondly, with our parameterisation, we investigate per-module hyperparameter optimisation and transfer. We characterise the empirical challenges of navigating the high-dimensional hyperparameter landscape, and propose practical guidelines for tackling this optimisation problem. We demonstrate that, with the right parameterisation, hyperparameter transfer holds even in the per-module hyperparameter regime. Our study covers an extensive range of optimisation hyperparameters of modern models: learning rates, AdamW parameters, weight decay, initialisation scales, and residual block multipliers. Our experiments demonstrate significant training speed improvements in Large Language Models with the transferred per-module hyperparameters.

Jakub Krajewski, Amitis Shidani, Dan Busbridge et al.

While scaling laws for Large Language Models (LLMs) traditionally focus on proxy metrics like pretraining loss, predicting downstream task performance has been considered unreliable. This paper challenges that view by proposing a direct framework to model the scaling of benchmark performance from the training budget. We find that for a fixed token-to-parameter ratio, a simple power law can accurately describe the scaling behavior of log accuracy on multiple popular downstream tasks. Our results show that the direct approach extrapolates better than the previously proposed two-stage procedure, which is prone to compounding errors. Furthermore, we introduce functional forms that predict accuracy across token-to-parameter ratios and account for inference compute under repeated sampling. We validate our findings on models with up to 17B parameters trained on up to 350B tokens across two dataset mixtures. To support reproducibility and encourage future research, we release the complete set of pretraining losses and downstream evaluation results.

Dan Busbridge, Amitis Shidani, Floris Weers et al. · apple-ml, berkeley

We propose a distillation scaling law that estimates distilled model performance based on a compute budget and its allocation between the student and teacher. Our findings mitigate the risks associated with large-scale distillation by enabling compute-optimal allocation for both the teacher and student to maximize student performance. We provide compute-optimal distillation recipes for two key scenarios: when a teacher already exists, and when a teacher needs training. In settings involving many students or an existing teacher, distillation outperforms supervised learning up to a compute level that scales predictably with student size. Conversely, if only one student is to be distilled and a teacher also requires training, supervised learning is generally preferable. Additionally, our large-scale study of distillation increases our understanding of the process and helps inform experimental design.

Samira Abnar, Harshay Shah, Dan Busbridge et al. · apple-ml

Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily defined by two dimensions: the number of model parameters and the compute per example. While scaling typically involves increasing both, the precise interplay between these factors and their combined contribution to overall capacity remains not fully understood. We explore this relationship in the context of sparse Mixture-of-Experts (MoEs), which allow scaling the number of parameters without proportionally increasing the FLOPs per example. We investigate how varying the sparsity level, i.e., the fraction of inactive parameters, impacts model's performance during pretraining and downstream few-shot evaluation. We find that under different constraints (e.g., parameter size and total training compute), there is an optimal level of sparsity that improves both training efficiency and model performance. These results provide a better understanding of the impact of sparsity in scaling laws for MoEs and complement existing works in this area, offering insights for designing more efficient architectures.

Jason Ramapuram, Eeshan Gunesh Dhekane, Amitis Shidani et al.

Speech-only spoken language models (SLMs) lag behind text and text-speech models in performance, with recent discrete autoregressive (AR) SLMs indicating significant computational and data demands to match text models. Since discretizing continuous speech for AR creates bottlenecks, we explore whether continuous diffusion (CD) SLM is more viable. To quantify the SLMs linguistic quality, we introduce the phoneme Jensen-Shannon divergence (pJSD) metric. Our analysis reveals CD SLMs, mirroring AR behavior, exhibit scaling laws for validation loss and pJSD, and show optimal token-to-parameter ratios decreasing as compute scales. However, for the latter, loss becomes insensitive to choice of data and model sizes, showing potential for fast inference. Scaling CD SLMs to 16B parameters with tens of millions of hours of conversational data enables generation of emotive, prosodic, multi-speaker, multilingual speech, though achieving long-form coherence remains a significant challenge.

Louis Bethune, David Grangier, Dan Busbridge et al.

A widespread strategy to obtain a language model that performs well on a target domain is to finetune a pretrained model to perform unsupervised next-token prediction on data from that target domain. Finetuning presents two challenges: (i) if the amount of target data is limited, as in most practical applications, the model will quickly overfit, and (ii) the model will drift away from the original model, forgetting the pretraining data and the generic knowledge that comes with it. We aim to derive scaling laws that quantify these two phenomena for various target domains, amounts of available target data, and model scales. We measure the efficiency of injecting pretraining data into the finetuning data mixture to avoid forgetting and mitigate overfitting. A key practical takeaway from our study is that injecting as little as 1% of pretraining data in the finetuning data mixture prevents the model from forgetting the pretraining set.

Mustafa Shukor, Louis Bethune, Dan Busbridge et al.

Large foundation models are typically trained on data from multiple domains, with the data mixture--the proportion of each domain used--playing a critical role in model performance. The standard approach to selecting this mixture relies on trial and error, which becomes impractical for large-scale pretraining. We propose a systematic method to determine the optimal data mixture for any target domain using scaling laws. Our approach accurately predicts the loss of a model of size $N$ trained with $D$ tokens and a specific domain weight vector $h$. We validate the universality of these scaling laws by demonstrating their predictive power in three distinct and large-scale settings: large language model (LLM), native multimodal model (NMM), and large vision models (LVM) pretraining. We further show that these scaling laws can extrapolate to new data mixtures and across scales: their parameters can be accurately estimated using a few small-scale training runs, and used to estimate the performance at larger scales and unseen domain weights. The scaling laws allow to derive the optimal domain weights for any target domain under a given training budget ($N$,$D$), providing a principled alternative to costly trial-and-error methods.

Amitis Shidani, Devon Hjelm, Jason Ramapuram et al. · apple-ml, berkeley

Contrastive learning typically matches pairs of related views among a number of unrelated negative views. Views can be generated (e.g. by augmentations) or be observed. We investigate matching when there are more than two related views which we call poly-view tasks, and derive new representation learning objectives using information maximization and sufficient statistics. We show that with unlimited computation, one should maximize the number of related views, and with a fixed compute budget, it is beneficial to decrease the number of unique samples whilst increasing the number of views of those samples. In particular, poly-view contrastive models trained for 128 epochs with batch size 256 outperform SimCLR trained for 1024 epochs at batch size 4096 on ImageNet1k, challenging the belief that contrastive models require large batch sizes and many training epochs.

Melika Ayoughi, Samira Abnar, Chen Huang et al. · apple-ml

The composition of objects and their parts, along with object-object positional relationships, provides a rich source of information for representation learning. Hence, spatial-aware pretext tasks have been actively explored in self-supervised learning. Existing works commonly start from a grid structure, where the goal of the pretext task involves predicting the absolute position index of patches within a fixed grid. However, grid-based approaches fall short of capturing the fluid and continuous nature of real-world object compositions. We introduce PART, a self-supervised learning approach that leverages continuous relative transformations between off-grid patches to overcome these limitations. By modeling how parts relate to each other in a continuous space, PART learns the relative composition of images-an off-grid structural relative positioning process that generalizes beyond occlusions and deformations. In tasks requiring precise spatial understanding such as object detection and time series prediction, PART outperforms strong grid-based methods like MAE and DropPos, while also maintaining competitive performance on global classification tasks with minimal hyperparameter tuning. By breaking free from grid constraints, PART opens up an exciting new trajectory for universal self-supervised pretraining across diverse datatypes-from natural images to EEG signals-with promising potential in video, medical imaging, and audio.

Polina Turishcheva, Jason Ramapuram, Sinead Williamson et al. · apple-ml, berkeley

Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, with Bayes by Backprop (BBB), a Bayesian method for estimating model posteriors. We find that the learned predictive std of BYOV vs. a supervised BBB model is well captured by a Gaussian distribution, providing preliminary evidence that the learned parameter posterior is useful for label free uncertainty estimation. BYOV improves upon the deterministic BYOL baseline (+2.83% test ECE, +1.03% test Brier) and presents better calibration and reliability when tested with various augmentations (eg: +2.4% test ECE, +1.2% test Brier for Salt & Pepper noise).

Claire Woodcock, Brent Mittelstadt, Dan Busbridge et al.

To achieve the promoted benefits of an AI symptom checker, laypeople must trust and subsequently follow its instructions. In AI, explanations are seen as a tool to communicate the rationale behind black-box decisions to encourage trust and adoption. However, the effectiveness of the types of explanations used in AI-driven symptom checkers has not yet been studied. Social theories suggest that why-explanations are better at communicating knowledge and cultivating trust among laypeople. This study ascertains whether explanations provided by a symptom checker affect explanatory trust among laypeople (N=750) and whether this trust is impacted by their existing knowledge of disease. Results suggest system builders developing explanations for symptom-checking apps should consider the recipient's knowledge of a disease and tailor explanations to each user's specific need. Effort should be placed on generating explanations that are personalized to each user of a symptom checker to fully discount the diseases that they may be aware of and to close their information gap.

Jason Ramapuram, Dan Busbridge, Xavier Suau et al.

While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent variables. In contrast, prescribed latent variable (LV) models enable attributing uncertainty, inducing task specific compression, and in general allow for more interpretable representations. In this work, we introduce LV approximations to large scale contrastive SSL models. We demonstrate that this addition improves downstream performance (resulting in 96.42% and 77.49% test top-1 fine-tuned performance on CIFAR10 and ImageNet respectively with a ResNet50) as well as producing highly compressed representations (588x reduction) that are useful for interpretability, classification and regression downstream tasks.

Jason Ramapuram, Dan Busbridge, Russ Webb

In this work we examine how fine-tuning impacts the fairness of contrastive Self-Supervised Learning (SSL) models. Our findings indicate that Batch Normalization (BN) statistics play a crucial role, and that updating only the BN statistics of a pre-trained SSL backbone improves its downstream fairness (36% worst subgroup, 25% mean subgroup gap). This procedure is competitive with supervised learning, while taking 4.4x less time to train and requiring only 0.35% as many parameters to be updated. Finally, inspired by recent work in supervised learning, we find that updating BN statistics and training residual skip connections (12.3% of the parameters) achieves parity with a fully fine-tuned model, while taking 1.33x less time to train.

Tom George Grigg, Dan Busbridge, Jason Ramapuram et al.

Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately learned. By leveraging recent advances in the comparison of neural representations, we explore in this direction by comparing a contrastive self-supervised algorithm to supervision for simple image data in a common architecture. We find that the methods learn similar intermediate representations through dissimilar means, and that the representations diverge rapidly in the final few layers. We investigate this divergence, finding that these layers strongly fit to their distinct learning objectives. We also find that the contrastive objective implicitly fits the supervised objective in intermediate layers, but that the reverse is not true. Our work particularly highlights the importance of the learned intermediate representations, and raises critical questions for auxiliary task design.

Joseph Enguehard, Dan Busbridge, Adam Bozson et al.

The modelling of Electronic Health Records (EHRs) has the potential to drive more efficient allocation of healthcare resources, enabling early intervention strategies and advancing personalised healthcare. However, EHRs are challenging to model due to their realisation as noisy, multi-modal data occurring at irregular time intervals. To address their temporal nature, we treat EHRs as samples generated by a Temporal Point Process (TPP), enabling us to model what happened in an event with when it happened in a principled way. We gather and propose neural network parameterisations of TPPs, collectively referred to as Neural TPPs. We perform evaluations on synthetic EHRs as well as on a set of established benchmarks. We show that TPPs significantly outperform their non-TPP counterparts on EHRs. We also show that an assumption of many Neural TPPs, that the class distribution is conditionally independent of time, reduces performance on EHRs. Finally, our proposed attention-based Neural TPP performs favourably compared to existing models, whilst aligning with real world interpretability requirements, an important step towards a component of clinical decision support systems.

Albert Buchard, Baptiste Bouvier, Giulia Prando et al.

Medical Triage is of paramount importance to healthcare systems, allowing for the correct orientation of patients and allocation of the necessary resources to treat them adequately. While reliable decision-tree methods exist to triage patients based on their presentation, those trees implicitly require human inference and are not immediately applicable in a fully automated setting. On the other hand, learning triage policies directly from experts may correct for some of the limitations of hard-coded decision-trees. In this work, we present a Deep Reinforcement Learning approach (a variant of DeepQ-Learning) to triage patients using curated clinical vignettes. The dataset, consisting of 1374 clinical vignettes, was created by medical doctors to represent real-life cases. Each vignette is associated with an average of 3.8 expert triage decisions given by medical doctors relying solely on medical history. We show that this approach is on a par with human performance, yielding safe triage decisions in 94% of cases, and matching expert decisions in 85% of cases. The trained agent learns when to stop asking questions, acquires optimized decision policies requiring less evidence than supervised approaches, and adapts to the novelty of a situation by asking for more information. Overall, we demonstrate that a Deep Reinforcement Learning approach can learn effective medical triage policies directly from expert decisions, without requiring expert knowledge engineering. This approach is scalable and can be deployed in healthcare settings or geographical regions with distinct triage specifications, or where trained experts are scarce, to improve decision making in the early stage of care.

Joseph Enguehard, Dan Busbridge, Vitalii Zhelezniak et al.

The choice of sentence encoder architecture reflects assumptions about how a sentence's meaning is composed from its constituent words. We examine the contribution of these architectures by holding them randomly initialised and fixed, effectively treating them as as hand-crafted language priors, and evaluating the resulting sentence encoders on downstream language tasks. We find that even when encoders are presented with additional information that can be used to solve tasks, the corresponding priors do not leverage this information, except in an isolated case. We also find that apparently uninformative priors are just as good as seemingly informative priors on almost all tasks, indicating that learning is a necessary component to leverage information provided by architecture choice.

Dan Busbridge, Dane Sherburn, Pietro Cavallo et al.

We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these methods to a wider variety of problems. A thorough evaluation of these models is performed, and comparisons are made against established benchmarks. To provide a meaningful comparison, we retrain Relational Graph Convolutional Networks, the spectral counterpart of Relational Graph Attention Networks, and evaluate them under the same conditions. We find that Relational Graph Attention Networks perform worse than anticipated, although some configurations are marginally beneficial for modelling molecular properties. We provide insights as to why this may be, and suggest both modifications to evaluation strategies, as well as directions to investigate for future work.

Vitalii Zhelezniak, Dan Busbridge, April Shen et al.

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal representation space, in which semantically close symbols are mapped to representations that are close under a similarity measure induced by the model's objective function. In addition, we present a straightforward procedure that, without any retraining or architectural modifications, allows deep recurrent models to perform equally well (and sometimes better) when compared to shallow models. To validate our analysis, we conduct a set of consistent empirical evaluations and introduce several new sentence embedding models in the process. Even though this work is presented within the context of natural language processing, the insights are readily applicable to other domains that rely on distributed representations for transfer tasks.