Canada

In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error distribution. However, a recent study suggested that the error distribution for training the value function is often skewed because of the properties of the Bellman operator, and violates the implicit assumption of normal error distribution in the least squares method. To address this, we proposed a method called Symmetric Q-learning, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution. We evaluated the proposed method on continuous control benchmark tasks in MuJoCo. It improved the sample efficiency of a state-of-the-art reinforcement learning method by reducing the skewness of the error distribution.

AAAI 2024

Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning

ml: reinforcement learning

ml: deep learning algorithms

rob: behavior learning & control

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

Spiking neural networks (SNNs) have garnered significant attention for their low power consumption when deployed on neuromorphic hardware that operates in orders of magnitude lower power than general-purpose hardware. Direct training methods for SNNs come with an inherent latency for which the SNNs are optimized, and in general, the higher the latency, the better the predictive powers of the models, but at the same time, the higher the energy consumption during training and inference. Furthermore, an SNN model optimized for one particular latency does not necessarily perform well in lower latencies, which becomes relevant in scenarios where it is necessary to switch to a lower latency because of the depletion of onboard energy or other operational requirements. In this work, we propose Stochastic Latency Training (SLT), a direct training method for SNNs that optimizes the model for the given latency but simultaneously offers a minimum reduction of predictive accuracy when shifted to lower inference latencies. We provide heuristics for our approach with partial theoretical justification and experimental evidence showing the state-of-the-art performance of our models on datasets such as CIFAR-10, DVS-CIFAR-10,  CIFAR-100, and DVS-Gesture. Our code is available at \url{https://github.com/srinuvaasu/SLT}

Enhancing Training of Spiking Neural Network with Stochastic Latency

While modern biotechnologies allow synthesizing new proteins and function measurements at scale, efficiently exploring a protein sequence space and engineering it remains a daunting task due to the vast sequence space of any given protein. Protein engineering is typically conducted through an iterative process of adding mutations to the wild-type or lead sequences, recombination of mutations, and running new rounds of screening. To enhance the efficiency of such a process, we propose a tree search-based bandit learning method, which expands a tree starting from the initial sequence with the guidance of a bandit machine learning model. Under simplified assumptions and a Gaussian Process prior, we provide theoretical analysis and a Bayesian regret bound, demonstrating that the method can efficiently discover a near-optimal design. The full algorithm is compatible with a suite of randomized tree search heuristics, machine learning models, pre-trained embeddings, and bandit techniques. We test various instances of the algorithm across benchmark protein datasets using simulated screens. Experiment results demonstrate that the algorithm is both sample-efficient, diversity-promoting, and able to find top designs using reasonably small mutation counts.

Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization

The past few years has witnessed the dominance of Graph Convolutional Networks (GCNs) over human motion prediction. Various styles of graph convolutions have been proposed, with each one meticulously designed and incorporated into a carefully-crafted network architecture. This paper breaks the limits of existing knowledge by proposing Universal Graph Convolution (UniGC), a novel graph convolution concept that re-conceptualizes different graph convolutions as its special cases. Leveraging UniGC on network-level, we propose GCNext, a novel GCN-building paradigm that dynamically determines the best-fitting graph convolutions both sample-wise and layer-wise. GCNext offers multiple use cases, including training a new GCN from scratch or refining a preexisting GCN. Experiments on Human3.6M, AMASS, and 3DPW datasets show that, by incorporating unique module-to-network designs, GCNext yields up to 9x lower computational cost than existing GCN methods, on top of achieving state-of-the-art performance. Our code is available at https://github.com/BradleyWang0416/GCNext.

GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction

Abstract argumentation is a reasoning model for evaluating arguments. Recently, gradual semantics has received considerable attention in weighted argumentation, which assigns an acceptability degree to each argument as its strength. In this paper, we aim to enhance gradual semantics by non-reciprocally incorporating the notion of rejectability degree. Such a setting offers a bilateral perspective on argument strength, enabling more comprehensive argument evaluations in practical situations. To this end, we first provide a set of principles for our semantics, taking both the acceptability and rejectability degrees into account, and propose three novel semantics conforming to the above principles. These semantics are defined as the limits of iterative sequences that always converge in any given weighted argumentation system, making them preferable for real-world applications.

Bilateral Gradual Semantics for Weighted Argumentation

Predicting chemical reaction yields is pivotal for efficient chemical synthesis, an area that focuses on the creation of novel compounds for diverse uses. 
Yield prediction demands accurate representations of reactions for forecasting practical transformation rates. Yet, the uncertainty issues broadcasting in real-world situations prohibit current models to excel in this task owing to the high sensitivity of yield activities and the uncertainty in yield measurements.  Existing models often utilize single-modal feature representations, such as molecular fingerprints, SMILES sequences, or molecular graphs, which is not sufficient to capture the complex interactions and dynamic behavior of molecules in reactions. In this paper, we present an advanced \underline{U}ncertainty-\underline{A}ware \underline{M}ultimodal model (UAM) to tackle these challenges. Our approach seamlessly integrates data sources from multiple modalities by encompassing sequence representations, molecular graphs, and expert-defined chemical reaction features for a comprehensive representation of reactions. Additionally, we address both the model and data-based uncertainty, refining the model's predictive capability. Extensive experiments on three datasets, including two high throughput experiment (HTE) datasets and one chemist-constructed Amide coupling reaction dataset, demonstrate that UAM outperforms the state-of-the-art methods. The code and used datasets are available at \url{https://github.com/jychen229/Multimodal-reaction-yield-prediction}.

Uncertainty-Aware Yield Prediction with Multimodal Molecular Features

Distributed optimization in resource constrained devices demands both communication efficiency and fast convergence rates. Newton-type methods are getting preferable due to their superior convergence rates compared to the first-order methods. In this paper, we study a new problem in regard to the second-order distributed optimization over unreliable networks. The working devices are power-limited or operate in unfavorable wireless channels, experiencing packet losses during their uplink transmission to the server. Our scenario is very common in real-world and leads to instability of classical distributed optimization methods especially the second-order methods because of their sensitivity to the imprecision of local Hessian matrices. To achieve robustness to high packet loss, communication efficiency and fast convergence rates, we propose a novel distributed second-order method, called RED-New Packet loss Resilient Distributed Approximate Newton. Each iteration of RED-New comprises two rounds of light-weight and lossy transmissions, in which the server aggregates the local information with a new developed scaling strategy. We prove the linear-quadratic convergence rate of RED-New. Experimental results demonstrate its advantage over first-order and second-order baselines, and its tolerance to packet loss rate ranging from 5% to 40%.

Communication Efficient Distributed Newton Method over Unreliable Networks

The recent criticisms of the robustness of post hoc model approximation explanation methods (like LIME and SHAP) have led to the rise of model-precise abductive explanations. For each data point, abductive explanations provide a minimal subset of features that are sufficient to generate the outcome. While theoretically sound and rigorous, abductive explanations suffer from a major issue --- there can be several valid abductive explanations for the same data point. In such cases, providing a single abductive explanation can be insufficient; on the other hand, providing all valid abductive explanations can be incomprehensible due to their size. In this work, we solve this issue by aggregating the many possible abductive explanations into feature importance scores. We propose three aggregation methods: two based on power indices from cooperative game theory and a third based on a well-known measure of causal strength. We characterize these three methods axiomatically, showing that each of them uniquely satisfies a set of desirable properties. We also evaluate them on multiple datasets and show that these explanations are robust to the attacks that fool SHAP and LIME.

Axiomatic Aggregations of Abductive Explanations

The recent large-scale pre-trained models like CLIP have aroused great concern in vision-language tasks. However, when required to match image-text data collected in a streaming manner, namely Continual Vision-Language Retrieval (CVRL), their performances are still limited due to the catastrophic forgetting of the learned old knowledge. To handle this issue, advanced methods are proposed to distill the affinity knowledge between images and texts from the old model to the new one for anti-forgetting. Unfortunately, existing approaches neglect the impact of incorrect affinity, which prevents the balance between the anti-forgetting of old knowledge and the acquisition of new knowledge. Therefore, we propose a novel framework called Dynamic Knowledge Rectification (DKR) that simultaneously achieves incorrect knowledge filtering and rectification. Specifically, we first filter the incorrect affinity knowledge calculated by the old model on the new data. Then, a knowledge rectification method is designed to rectify the incorrect affinities while preserving the correct ones. In particular, for the new data that can only be correctly retrieved by the new model, we rectify them with the corresponding new affinity to protect them from negative transfer. Additionally, for those that can not be retrieved by either the old or the new model, we introduce paired ground-truth labels to promote the acquisition of both old and new knowledge. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our DKR and its superiority against state-of-the-art methods.

Continual Vision-Language Retrieval via Dynamic Knowledge Rectification

Large Language Models (LLMs) have demonstrated impressive performance in natural language processing tasks by leveraging chain of thought (CoT) that enables step-by-step thinking. Extending LLMs with multimodal capabilities is the recent interest, but incurs computational cost and requires substantial hardware resources. To address these challenges, we propose KAM-CoT a framework that integrates CoT reasoning, Knowledge Graphs (KGs), and multiple modalities for a comprehensive understanding of multimodal tasks. KAM-CoT adopts a two-stage training process with KG grounding to generate effective rationales and answers. By incorporating external knowledge from KGs during reasoning, the model gains a deeper contextual understanding reducing hallucinations and enhancing the quality of answers. This knowledge-augmented CoT reasoning empowers the model to handle questions requiring external context, providing more informed answers. Experimental findings show KAM-CoT outperforms the state-of-the-art methods. On the ScienceQA dataset, we achieve an average accuracy of 93.87%, surpassing GPT-3.5 (75.17%) by 18% and GPT-4 (83.99%) by 10%. Remarkably, KAM-CoT achieves these results with only 280M trainable parameters at a time, demonstrating its cost-efficiency and effectiveness.

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning

Most planners are based on grounding, that is, generating all instances of a parameterized action during a preprocessing phase.
For some problems the number of ground actions is too high, causing a performance bottleneck.
Building upon an existing approach, we present an enhanced method to split action schemas automatically during the grounding phase, to reduce the number of ground actions.
First, we propose to exploit the structural knowledge of the problems to have a more informative dependency graph.
Then, we suggest a better objective function to define and choose the best split.
Finally, we present a more effective search to find it.
We experimentally measure the impact of each of these improvements, and show that our approach significantly outperforms the state of the art.

Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning

Downloads

Next from AAAI 2024

Enhancing Training of Spiking Neural Network with Stochastic Latency

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

Enhancing Training of Spiking Neural Network with Stochastic Latency

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads