ICML 2024 Papers

Mixup, which generates synthetic training samples on the data manifold, has been shown to be highly effective in augmenting Euclidean data. However, finding a proper data manifold for graph data is non-trivial, as graphs are non-Euclidean data in disparate spaces. Though efforts have been made, most of the existing graph mixup methods neglect the intrinsic geodesic guarantee, thereby generating inconsistent sample-label pairs. To address this issue, we propose GeoMix to mixup graphs on the Gromov-Wasserstein (GW) geodesics. A joint space over input graphs is first defined based on the GW distance, and graphs are then transformed into the GW space through equivalence-preserving transformations. We further show that the linear interpolation of the transformed graph pairs defines a geodesic connecting the original pairs on the GW manifold, hence ensuring the consistency between generated samples and labels. An accelerated mixup algorithm on the approximate low-dimensional GW manifold is further proposed. Extensive experiments show that the proposed GeoMix promotes the generalization and robustness of GNN models.

In class-imbalanced learning, the scarcity of information about minority classes presents challenges in obtaining generalizable features for these classes. Leveraging large-scale pre-trained models with powerful generalization capabilities as teacher models can help fill this information gap. Traditional knowledge distillation transfers the label distribution $p(\boldsymbol{y}|\boldsymbol{x})$ predicted by the teacher model to the student model. However, this method falls short on imbalanced data as it fails to capture the class-conditional probability distribution $p(\boldsymbol{x}|\boldsymbol{y})$ from the teacher model, which is crucial for enhancing generalization. To overcome this, we propose Class-Conditional Knowledge Distillation (CCKD), a novel approach that enables learning of the teacher model’s class-conditional probability distribution during the distillation process. Additionally, we introduce Augmented CCKD (ACCKD), which involves distillation on a constructed class-balanced dataset (formed through data mixing) and feature imitation on the entire dataset to further facilitate the learning of features. Experimental results on various imbalanced datasets demonstrate an average accuracy improvement of 7.4% using our method.

Graph self-supervised learning has sparked a research surge in training informative representations without accessing any labeled data. However, our understanding of graph self-supervised learning remains limited, and the inherent relationships between various self-supervised tasks are still unexplored. Our paper aims to provide a fresh understanding of graph self-supervised learning based on task correlations. Specifically, we evaluate the performance of the representations trained by one specific task on other tasks and define correlation values to quantify task correlations. Through this process, we unveil the task correlations between various self-supervised tasks and can measure their expressive capabilities, which are closely related to downstream performance. By analyzing the correlation values between tasks across various datasets, we reveal the complexity of task correlations and the limitations of existing multi-task learning methods. To obtain more capable representations, we propose Graph Task Correlation Modeling (GraphTCM) to illustrate the task correlations and utilize it to enhance graph self-supervised training. The experimental results indicate that our method significantly outperforms existing methods across various downstream tasks.

Knowledge Distillation (KD) has evolved into a practical technology for transferring knowledge from a well-performing model (teacher) to a weak model (student). A counter-intuitive phenomenon known as capacity mismatch has been identified, wherein KD performance may not be good when a better teacher instructs the student. Various preliminary methods have been proposed to alleviate capacity mismatch, but a unifying explanation for its cause remains lacking. In this paper, we propose *a unifying analytical framework to pinpoint the core of capacity mismatch based on calibration*. Through extensive analytical experiments, we observe a positive correlation between the calibration of the teacher model and the KD performance with original KD methods. As this correlation arises due to the sensitivity of metrics (e.g., KL divergence) to calibration, we recommend employing measurements insensitive to calibration such as ranking-based loss. Our experiments demonstrate that ranking-based loss can effectively replace KL divergence, aiding large models with poor calibration to teach better.

Directed evolution, a cornerstone of protein optimization, is to harness natural mutational processes to enhance protein functionality. Existing Machine Learning-assisted Directed Evolution (MLDE) methodologies typically rely on data-driven strategies and often overlook the profound domain knowledge in biochemical fields. In this paper, we introduce a novel Knowledge-aware Reinforced Language Model (KnowRLM) for MLDE. An Amino Acid Knowledge Graph (AAKG) is constructed to represent the intricate biochemical relationships among amino acids. We further propose a Protein Language Model (PLM)-based policy network that iteratively samples mutants through preferential random walks on the AAKG using a dynamic sliding window mechanism. The novel mutants are actively sampled to fine-tune a fitness predictor as the reward model, providing feedback to the knowledge-aware policy. Finally, we optimize the whole system in an active learning approach that mimics biological settings in practice.KnowRLM stands out for its ability to utilize contextual amino acid information from knowledge graphs, thus attaining advantages from both statistical patterns of protein sequences and biochemical properties of amino acids.Extensive experiments demonstrate the superior performance of KnowRLM in more efficiently identifying high-fitness mutants compared to existing methods.

In this paper, we study semi-supervised graph classification, which aims at accurately predicting the categories of graphs in scenarios with limited labeled graphs and abundant unlabeled graphs. Despite the promising capability of graph neural networks (GNNs), they typically require a large number of costly labeled graphs, while a wealth of unlabeled graphs fail to be effectively utilized. Moreover, GNNs are inherently limited to encoding local neighborhood information using message-passing mechanisms, thus lacking the ability to model higher-order dependencies among nodes. To tackle these challenges, we propose a Hypergraph-Enhanced DuAL framework named HEAL for semi-supervised graph classification, which captures graph semantics from the perspective of the hypergraph and the line graph, respectively. Specifically, to better explore the higher-order relationships among nodes, we design a hypergraph structure learning to adaptively learn complex node dependencies beyond pairwise relations. Meanwhile, based on the learned hypergraph, we introduce a line graph to capture the interaction between hyperedges, thereby better mining the underlying semantic structures. Finally, we develop a relational consistency learning to facilitate knowledge transfer between the two branches and provide better mutual guidance. Extensive experiments on real-world graph datasets verify the effectiveness of the proposed method against existing state-of-the-art methods.

Current directed graph embedding methods build upon undirected techniques but often inadequately capture directed edge information, leading to challenges such as: (1) Suboptimal representations for nodes with low in/out-degrees, due to the insufficient neighbor interactions; (2) Limited inductive ability for representing new nodes post-training; (3) Narrow generalizability, as training is overly coupled with specific tasks. In response, we propose DUPLEX, an inductive framework for complex embeddings of directed graphs. It (1) leverages Hermitian adjacency matrix decomposition for comprehensive neighbor integration, (2) employs a dual GAT encoder for directional neighbor modeling, and (3) features two parameter-free decoders to decouple training from particular tasks. DUPLEX outperforms state-of-the-art models, especially for nodes with sparse connectivity, and demonstrates robust inductive capability and adaptability across various tasks. The code will be available upon publication.

In Federated Continual Learning (FCL), the challenge lies in effectively facilitating knowledge transfer and enhancing the performance across various tasks on different clients. Current FCL methods predominantly focus on avoiding interference between tasks, thereby overlooking the potential for positive knowledge transfer across tasks learned by different clients at separate time intervals. To address this issue, we introduce a **P**rompt-based kn**ow**le**d**ge transf**er** FCL algorithm, called **Powder**, designed to effectively foster the transfer of knowledge encapsulated in prompts between various sequentially learned tasks and clients. Furthermore, we have devised a unique approach for prompt generation and aggregation, intending to alleviate privacy protection concerns and communication overhead, while still promoting knowledge transfer. Comprehensive experimental results demonstrate the superiority of our method in terms of reduction in communication costs, and enhancement of knowledge transfer. Code is available at https://github.com/piaohongming/Powder.

Despite their exceptional capabilities, large language models (LLMs) are prone to generating unintended text due to false or outdated knowledge. Given the resource-intensive nature of retraining LLMs, there has been a notable increase in the development of knowledge editing. However, current approaches and evaluations rarely explore the perturbation of editing on neighboring knowledge. This paper studies whether updating new knowledge to LLMs perturbs the neighboring knowledge encapsulated within them. Specifically, we seek to figure out whether appending a new answer into an answer list to a factual question leads to catastrophic forgetting of original correct answers in this list, as well as unintentional inclusion of incorrect answers. A metric of additivity is introduced and a benchmark dubbed as Perturbation Evaluation of Appending Knowledge (PEAK) is constructed to evaluate the degree of perturbation to neighboring knowledge when appending new knowledge. Besides, a plug-and-play framework termed Appending via Preservation and Prevention (APP) is proposed to mitigate the neighboring perturbation by maintaining the integrity of the answer list. Experiments demonstrate the effectiveness of APP coupling with four editing methods on three LLMs.

Self-supervised learning (SSL) has gained increasing attention in the graph learning community, owing to its capability of enabling powerful models pre-trained on large unlabeled graphs for general purposes, facilitating quick adaptation to specific domains. Though promising, existing graph SSL frameworks often struggle to capture both high-level abstract features and fine-grained features simultaneously, leading to sub-optimal generalization abilities across different downstream tasks. To bridge this gap, we present Multi-granularity Graph Semantic Ensemble via Knowledge Distillation, namely MGSE, a plug-and-play graph knowledge distillation framework that can be applied to any existing graph SSL framework to enhance its performance by incorporating the concept of multi-granularity. Specifically, MGSE captures multi-granular knowledge by employing multiple student models to learn from a single teacher model, conditioned by probability distributions with different granularities. We apply it to six state-of-the-art graph SSL frameworks and evaluate their performances over multiple graph datasets across different domains, the experimental results show that MGSE can consistently boost the performance of these existing graph SSL frameworks with up to 9.2% improvement.

Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest. Retrieval-augmented language model (RALM)---which enhances models with up-to-date knowledge---emerges as a promising method to reduce hallucination. However, existing RALMs may instead exacerbate hallucination when retrieving lengthy contexts. To address this challenge, we propose COFT, a novel **CO**arse-to-**F**ine highligh**T**ing method to focus on different granularity-level key texts, thereby avoiding getting lost in lengthy contexts. Specifically, COFT consists of three components: *recaller*, *scorer*, and *selector*. First, *recaller* applies a knowledge graph to extract potential key entities in a given context. Second, *scorer* measures the importance of each entity by calculating its contextual weight. Finally, *selector* selects high contextual weight entities with a dynamic threshold algorithm and highlights the corresponding paragraphs, sentences, or words in a coarse-to-fine manner. Extensive experiments on knowledge hallucination benchmark demonstrate the effectiveness of COFT, leading to a superior performance over 30% in F1 score metric. Moreover, COFT also exhibits remarkable versatility across various long-form tasks, such as reading comprehension and question answering.

Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information. Prior works have proposed a variety of graph rewiring concepts that aim at optimizing the spatial or spectral properties of graphs to promote the signal propagation. However, such approaches inevitably deteriorate the original graph topology, which may lead to a distortion of information flow. To address this, we introduce an ex**pand**ed width-**a**ware (**PANDA**) message passing, a new message passing paradigm where nodes with high centrality, a potential source of over-squashing, are selectively expanded in width to encapsulate the growing influx of signals from distant nodes. Experimental results show that our method outperforms existing rewiring methods, suggesting that selectively expanding the hidden state of nodes can be a compelling alternative to graph rewiring for addressing the over-squashing.

The Weisfeiler--Leman algorithm (1-WL) is a well-studied heuristic for the graph isomorphism problem. Recently, the algorithm has played a prominent role in understanding the expressive power of message-passing graph neural networks (MPNNs) and being effective as a graph kernel. Despite its success, the 1-WL faces challenges in distinguishing non-isomorphic graphs, leading to the development of more expressive MPNN and kernel architectures. However, the relationship between enhanced expressivity and improved generalization performance remains unclear. Here, we show that an architecture's expressivity offers limited insights into its generalization performance when viewed through graph isomorphism. Moreover, we focus on augmenting 1-WL and MPNNs with subgraph information and employ classical margin theory to investigate the conditions under which an architecture's increased expressivity aligns with improved generalization performance. In addition, we introduce variations of expressive 1-WL-based kernel and MPNN architectures with provable generalization properties. Our empirical study confirms the validity of our theoretical findings.

Deep learning methods, including deep multiple instance learning methods, have been criticized for their limited ability to incorporate domain knowledge. A reason that knowledge incorporation is challenging in deep learning is that the models usually lack a mapping between their model components and the entities of the domain, making it a non-trivial task to incorporate probabilistic prior information. In this work, we show that such a mapping between domain entities and model components can be defined for a multiple instance learning setting and propose a framework DeeMILIP that encompasses multiple strategies to exploit this mapping for prior knowledge incorporation. We motivate and formalize these strategies from a probabilistic perspective. Experiments on an immune-based diagnostics case show that our proposed strategies allow to learn generalizable models even in settings with weak signals, limited dataset size, and limited compute.

Knowledge graph reasoning plays a vital role in various applications and has garnered considerable attention. Recently, path-based methods have achieved impressive performance. However, they may face limitations stemming from constraints in message-passing neural networks, such as missing paths and information over-squashing. In this paper, we revisit the application of transformers for knowledge graph reasoning to address the constraints faced by path-based methods and propose a novel method KnowFormer. KnowFormer utilizes a transformer architecture to perform reasoning on knowledge graphs from the message-passing perspective, rather than reasoning by textual information like previous pretrained language model based methods. Specifically, we define the attention computation based on the query prototype of knowledge graph reasoning, facilitating convenient construction and efficient optimization. To incorporate structural information into the self-attention mechanism, we introduce structure-aware modules to calculate query, key, and value respectively. Additionally, we present an efficient attention computation method for better scalability. Experimental results demonstrate the superior performance of KnowFormer compared to prominent baseline methods on both transductive and inductive benchmarks.

Maximum matching is one of the most fundamental combinatorial optimization problems with applications in various contexts such as balanced clustering, data mining, resource allocation, and online advertisement. In many of these applications, the input graph is massive. The sheer size of these inputs makes it impossible to store the whole graph in the memory of a single machine and process it there. Graph sparsification has been an extremely powerful tool to alleviate this problem. In this paper, we study a highly successful and versatile sparsifier for the matching problem: the *edge-degree constrained subgraph (EDCS)* introduced first by Bernstein & Stein 2015 The EDCS has a parameter $\beta \geq 2$ which controls the density of the sparsifier. It has been shown through various proofs in the literature that by picking a subgraph with $O(n\beta)$ edges, the EDCS includes a matching of size at least $2/3-O(1/\beta)$ times the maximum matching size. As such, by increasing $\beta$ the approximation ratio of EDCS gets closer and closer to $2/3$. In this paper, we propose a new approach for analyzing the approximation ratio of EDCS. Our analysis is *tight* for any value of $\beta$. Namely, we pinpoint the precise approximation ratio of EDCS for any sparsity parameter $\beta$. Our analysis reveals that one does not necessarily need to increase $\beta$ to improve approximation, as suggested by previous analysis. In particular, the best choice turns out to be $\beta = 6$, which achieves an approximation ratio of $.677$! This is arguably surprising as it is even better than $2/3 \sim .666$, the bound that was widely believed to be the limit for EDCS.

Both the marginal contributions needed for the computation of Shapley values and the graph produced by Pearl-Verma theorem rely on the choice of an ordering of the variables. For Shapley values, the marginal contributions are averaged over all orderings, while in causal inference methods, the typical approach is to select orderings producing a graph with a minimal number of edges. We reconcile both approaches by reinterpreting them from a maximum entropy perspective. Namely, Shapley values assume no prior knowledge about the orderings and treat them as equally likely, while causal inference approaches apply Occam's razor and consider only orderings producing the simplest explanatory graphs. We find that the blind application of Occam's razor to Shapley values does not produce fully satisfactory explanations. Hence, we propose two variations of Shapley values based on entropy maximization to appropriately incorporate prior information about the model. Hence, we propose a variation of Shapley values based on entropy maximization to appropriately incorporate prior information about the model.

We warn against a common but incomplete understanding of empirical research in machine learning that leads to non-replicable results, makes findings unreliable, and threatens to undermine progress in the field. To overcome this alarming situation, we call for more awareness of the plurality of ways of gaining knowledge experimentally but also of some epistemic limitations. In particular, we argue most current empirical machine learning research is fashioned as confirmatory research while it should rather be considered exploratory.

We introduce the E$^4$ algorithm for the batched linear bandit problem, incorporating an Explore-Estimate-Eliminate-Exploit framework. With a proper choice of exploration rate, we prove E$^4$ achieves the finite-time minimax optimal regret with only $O(\log\log T)$ batches, and the asymptotically optimal regret with only $3$ batches as $T\rightarrow\infty$, where $T$ is the time horizon. We further prove a lower bound on the batch complexity of liner contextual bandits showing that any asymptotically optimal algorithm must require at least $3$ batches in expectation as $T\rightarrow \infty$, which indicates E$^4$ achieves the asymptotic optimality in regret and batch complexity simultaneously. To the best of our knowledge, E$^4$ is the first algorithm for linear bandits that simultaneously achieves the minimax and asymptotic optimality in regret with the corresponding optimal batch complexities. In addition, we show that with another choice of exploration rate E$^4$ achieves an instance-dependent regret bound requiring at most $O(\log T)$ batches, and maintains the minimax optimality and asymptotic optimality. We conduct thorough experiments to evaluate our algorithm on randomly generated instances and the challenging *End of Optimism* instances (Lattimore & Szepesvari, 2017) which were shown to be hard to learn for optimism based algorithms. Empirical results show that E$^4$ consistently outperforms baseline algorithms with respect to regret minimization, batch complexity, and computational efficiency.