Create and explore imaginative 3D worlds with our new product Dreamfield (opens in a new tab)
Papers
Topics
Authors
Recent
Search
2000 character limit reached

Simplicial Embeddings in Topology & Machine Learning

Updated 16 July 2026
  • Simplicial embeddings are maps that preserve the incidence and homological structure of simplicial complexes when embedded in geometric spaces.
  • They enable various methodologies including isometric, spectral, and simplex-constrained latent embeddings in fields like topology, geometry, and machine learning.
  • Applications range from trajectory analysis and reinforcement learning to complex representation learning, addressing challenges such as high-dimensional structure preservation and computational complexity.

Searching arXiv for relevant papers on “simplicial embeddings” across topology, geometry, and machine learning. Simplicial embeddings denote a family of constructions in which simplices, simplicial complexes, higher-order signals, or simplex-constrained latent codes are placed into another geometric or representation space while preserving selected structure. In the cited literature, the term covers continuous, PL, linear, geodesic, and isometric embeddings of simplicial complexes into SdS^d, Rd\mathbb{R}^d, and Minkowski space, as well as spectral embeddings of edge-flows, Hasse-diagram embeddings of simplices, and latent representations constrained to products of probability simplices (Frick et al., 2021, Minemyer, 2012, Frantzen et al., 2021, Lavoie et al., 2022).

1. Formal scope and recurring mathematical structures

A simplex is the convex hull of finitely many affinely independent points, and an abstract simplicial complex is a family of simplices closed under taking faces. In combinatorial treatments, $0$-simplices are vertices, $1$-simplices are edges, $2$-simplices are triangles, and higher-dimensional simplices encode higher-order interactions. Several of the cited works use the canonical probability simplex

Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},

either as a geometric object in its own right or as a constraint set for latent variables (Billings et al., 2019, Ren et al., 2023, Obando-Ceron et al., 15 Oct 2025).

A second recurrent structure is the simplicial incidence calculus. For a simplicial complex with vertex–edge incidence matrix B1B_1 and edge–triangle incidence matrix B2B_2, the unnormalized Hodge $1$-Laplacian is

L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.

This operator governs edge-flows and yields the Hodge decomposition

Rd\mathbb{R}^d0

where the harmonic space Rd\mathbb{R}^d1 is isomorphic to the first homology and therefore records holes in the underlying complex (Frantzen et al., 2021).

A third recurring meaning is architectural rather than topological. In simplex-constrained latent models, an encoder output is reshaped into Rd\mathbb{R}^d2 blocks of size Rd\mathbb{R}^d3, and each block is mapped by a temperature-scaled softmax to Rd\mathbb{R}^d4: Rd\mathbb{R}^d5 The resulting representation lies in Rd\mathbb{R}^d6, and each block can be interpreted as barycentric coordinates over a learned set of vertices (Obando-Ceron et al., 15 Oct 2025, Lavoie et al., 2022).

2. Embeddings of simplicial complexes into geometric spaces

In topological and metric geometry, simplicial embeddings are maps from the geometric realization of a simplicial complex into a sphere, Euclidean space, or pseudo-Euclidean space that preserve the simplicial structure in an appropriate sense. The strongest forms are simplicial isometric embeddings, where the edge-squared lengths prescribed on the complex agree with the pullback of the ambient bilinear form. For an indefinite metric polyhedron, a simplicial isometric map into Rd\mathbb{R}^d7 preserves the signed squared lengths

Rd\mathbb{R}^d8

where Rd\mathbb{R}^d9 is the Minkowski inner product (Minemyer, 2012, Galashin et al., 2015).

A sharp few-vertex sphere-embeddability criterion is available for complexes on $0$0 vertices. If $0$1 is a simplicial complex with $0$2 and $0$3 denotes its family of minimal non-faces, then

$0$4

For this regime, continuous embeddability into $0$5 or $0$6 is equivalent to geodesic or linear embeddability, yielding a Fáry-type rigidity phenomenon for complexes on $0$7 vertices (Frick et al., 2021).

For indefinite metric polyhedra, existence theorems depend on the maximal vertex degree or degeneracy. A compact $0$8-dimensional indefinite metric polyhedron with maximal degree $0$9 admits a simplicial isometric embedding into $1$0, where $1$1, and a PL isometric embedding into $1$2 when simpliciality is relaxed (Minemyer, 2012). A later constructive result shows that a possibly non-compact $1$3-dimensional $1$4-degenerate indefinite metric polyhedron admits a simplicial isometric map into $1$5, and if $1$6 then a simplicial isometric embedding into $1$7. The same work proves an extension theorem: every partial simplicial isometric embedding in $1$8-general position extends to a simplicial isometric embedding of the whole space (Galashin et al., 2015).

A different constructive direction is provided by parsimonious cones. For a finite $1$9-dimensional simplicial complex $2$0 with $2$1 simplices and any $2$2, there exists a triple $2$3 of simplicial complexes with bounded degrees such that $2$4, $2$5 is homotopy equivalent to $2$6, $2$7, and $2$8 and $2$9 are bounded by Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},0. A related local simplification theorem produces a homotopy equivalent bounded-degree complex Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},1 with Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},2 (Berdnikov, 2022).

3. Local criteria, rigidity, and extremal consequences

For Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},3-complexes in Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},4-space, embeddability can be characterized through local rotation data. A finite simply connected Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},5-dimensional simplicial complex embeds in Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},6 if and only if it has a planar rotation system, meaning that every vertex link graph embeds in the plane with edge-compatible cyclic orders. Under the additional condition Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},7 for some prime Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},8, embeddability is equivalent to the conjunction of Δk={α∈Rk+1:∑i=1k+1αi=1, αi≥0},\Delta^k=\{\alpha\in\mathbb{R}^{k+1}:\sum_{i=1}^{k+1}\alpha_i=1,\ \alpha_i\ge 0\},9 and existence of a planar rotation system (Carmesin, 2017).

Codimension-one embedding imposes a distinct homological obstruction. If a B1B_10-dimensional simplicial complex B1B_11 PL-embeds in B1B_12, then B1B_13 has a B1B_14-complete basis. Writing B1B_15 for the girth, defined as the minimum number of B1B_16-faces in a subcomplex with nontrivial top homology over B1B_17, the paper derives the inequality

B1B_18

Combined with Euler–Poincaré and strong Morse inequalities, this yields upper bounds on B1B_19 in terms of lower-dimensional face numbers and Betti numbers (Björner et al., 2016).

For complexes embeddable in the Euclidean B2B_20-space, links of vertices satisfy a stronger higher-order restriction. If B2B_21 is a PL embedding of a B2B_22-complex, then for any three vertices the intersection of their link-complexes is linklessly embeddable in B2B_23. This leads to the upper bound

B2B_24

for the maximum number of B2B_25-simplices in an embeddable B2B_26-complex on B2B_27 vertices. In the case B2B_28, the triple intersection of link-complexes is in fact planar (Parsa, 2015).

In geometric group theory and low-dimensional topology, “simplicial embedding” often means an injective adjacency-preserving map between combinatorial complexes associated to a surface. For multiarc graphs B2B_29, if $1$0 are non-exceptional, $1$1, $1$2, and $1$3, then any simplicial embedding $1$4 is induced by a $1$5-injective embedding $1$6 together with a fixed $1$7-multiarc, and its image is strongly convex (Parlier et al., 2019). An analogous theorem holds for $1$8-multicurve graphs $1$9, where simplicial embeddings are induced by L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.0-injective embeddings of surfaces and a fixed multicurve, and the automorphism groups satisfy L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.1 under the stated complexity hypotheses (Erlandsson et al., 2015).

4. Spectral, Hodge, and neural representation embeddings

A spectral interpretation of simplicial embeddings appears in trajectory analysis on discretized manifolds. A trajectory is encoded as an edge-flow L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.2, where each oriented edge receives L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.3, L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.4, or L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.5 according to traversal direction. If L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.6 contains the harmonic eigenvectors of the Hodge L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.7-Laplacian L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.8 corresponding to zero eigenvalues, then the flattened simplicial embedding is

L1=B1⊤B1+B2B2⊤.L_1=B_1^\top B_1+B_2B_2^\top.9

Each coordinate records circulation around a homological cycle, so the embedding is low-dimensional and topologically interpretable. In the synthetic experiments reported in the paper, Local Outlier Factor and Isolation Forest identify planted outliers in this harmonic space, and in the whale dataset the method isolates trajectories with atypical circulation around Hudson Bay and Hudson Strait (Frantzen et al., 2021).

Simplex2Vec adopts a different route. It performs random walks on the Hasse diagram of a simplicial complex and trains a skip-gram model with negative sampling on the resulting sequences, thereby embedding vertices and higher-dimensional simplices jointly. The method uses either uniform transitions or bias schemes that favor higher-order or lower-order simplices, and it was evaluated on Costa–Farber random complexes, sociopatterns school data, and fMRI connectivity. The reported results show that increasing maximal simplex dimension can materially change persistent-homology summaries and improve community detection when higher-order bias is used (Billings et al., 2019).

Entire-complex representation learning extends the same idea from simplex-level to complex-level embeddings. In “Simplicial Complex Representation Learning,” geometric message passing uses adjacency, coadjacency, boundary, and coboundary operators to produce simplex embeddings Rd\mathbb{R}^d00, and then pools them into a complex embedding

Rd\mathbb{R}^d01

Training minimizes

Rd\mathbb{R}^d02

so that Euclidean distances in the learned embedding space approximate a chosen complex-to-complex distance Rd\mathbb{R}^d03. On the deformation-transfer mesh dataset, the learned Rd\mathbb{R}^d04-dimensional embeddings cluster shapes by category and generalize to unseen categories (Hajij et al., 2021).

The same Hodge-theoretic perspective has also been used for semantic-native communication. In that setting, a transmitter maps data to a Rd\mathbb{R}^d05-order simplicial complex, computes simplicial embeddings through a simplicial convolutional autoencoder, and transmits the latent representation through an AWGN channel. The receiver reconstructs both the simplicial Laplacians and the simplex features. On a Semantic Scholar Open Research Corpus experiment, the reported system reconstructs missing data with Rd\mathbb{R}^d06 accuracy, remains stable under channel noise, and outperforms a conventional linear autoencoder that does not use simplicial structure (Zhao et al., 2022).

5. Simplex-constrained latent embeddings in machine learning

A recent line of work uses “simplicial embeddings” to denote latent vectors explicitly constrained to products of probability simplices. In self-supervised learning, a representation Rd\mathbb{R}^d07 is split into Rd\mathbb{R}^d08 blocks of dimension Rd\mathbb{R}^d09, each block is mapped by temperature-scaled softmax to Rd\mathbb{R}^d10, and the final representation Rd\mathbb{R}^d11 lies in Rd\mathbb{R}^d12. The cited theory shows that for downstream classification the SEM-normalized representation yields a tighter generalization bound than an unnormalized baseline, with the complexity term improving as Rd\mathbb{R}^d13. Empirically, SEM improves linear-probe performance for SimCLR, MoCo-v2, BYOL, Barlow Twins, SwAV, DINO, and VicReg on CIFAR-100, and improves BYOL on ImageNet from Rd\mathbb{R}^d14 to Rd\mathbb{R}^d15 top-1 while also improving ImageNet-V2, ImageNet-R, ImageNet-C, and ImageNet-A robustness benchmarks (Lavoie et al., 2022).

The same product-of-simplexes construction has been combined with iterated learning for compositional generalization. Here a teacher produces one-hot pseudo-labels sampled from each simplex block, a student matches them by a multi-label cross-entropy imitation loss, and then the student is fine-tuned on the downstream task before becoming the next teacher. The motivation is explicitly tied to Kolmogorov complexity: compositional bijections admit shorter descriptions than arbitrary bijections, and iterated learning biases the model toward compressible, reusable codes. The reported results show that neither SEM-only nor iterated-learning-only suffices on the controlled vision tasks, whereas the combination improves compositional generalization and also improves molecular property prediction on ogbg-molhiv, ogbg-molpcba, and PCQM4Mv2 (Ren et al., 2023).

In actor–critic reinforcement learning, simplicial embeddings are used as lightweight representation layers placed at the penultimate layer of an actor or critic network. Each block is constrained to a simplex by softmax, producing sparse, bounded, and often near-discrete features. The paper argues that this geometric inductive bias preserves feature covariance trace, stabilizes effective rank under drift, reduces neuron dormancy, and keeps gradient energy large. When inserted into FastTD3, FastSAC, and PPO, SEM improves sample efficiency and asymptotic return across HumanoidBench, IsaacGym, MTBench MT50, Atari-10, and a Booster T1 sim-to-real setup, with effectively no runtime penalty. The strongest gains are reported for actor-only placement at the penultimate layer, and the method uses standard softmax rather than straight-through estimators, sparsemax, or entmax (Obando-Ceron et al., 15 Oct 2025).

6. Applications, limitations, and open directions

Combinatorial surface theory supplies another application domain. A simplicial surface can be encoded through incidences of vertices, edges, and triangular faces, and its face graph is cubic. In this setting, umbrella cycles define a cycle double cover, and embeddings of cubic graphs on simplicial surfaces correspond to strong graph embeddings. For Rd\mathbb{R}^d16-connected cubic planar graphs, the induced embedding on a vertex-faithful simplicial sphere is unique up to isomorphism; the same paper classifies embeddings on simplicial projective planes, tori, and Klein bottles by Rd\mathbb{R}^d17-orbits of specified subgraphs in the planar dual Rd\mathbb{R}^d18 (Weiß et al., 2024).

The literature also records sharp negative results. At the geometric level, the complexity of embeddings can grow exponentially even when embeddability is topologically unobstructed. For each Rd\mathbb{R}^d19, there are families of Rd\mathbb{R}^d20-complexes Rd\mathbb{R}^d21 with bounded local combinatorial complexity such that every embedding has thickness at most Rd\mathbb{R}^d22, and the refinement complexity satisfies Rd\mathbb{R}^d23. In codimensions Rd\mathbb{R}^d24 and Rd\mathbb{R}^d25, and in a relative codimension-Rd\mathbb{R}^d26 setting, the paper further shows non-recursive lower-bound phenomena for refinement complexity (Freedman et al., 2013).

At the algorithmic and modeling level, the limitations are domain-specific. Spectral and Hasse-diagram methods depend on the correctness of the underlying simplicial complex, so coarse discretization, mis-specified holes, or high maximal simplex order can blur the intended structure or make Hasse construction expensive (Frantzen et al., 2021, Billings et al., 2019). Simplex-constrained latent models introduce hyperparameters such as the number of blocks, block size, and temperature, and the cited reinforcement-learning work notes that benefits may be smaller under extreme distribution shift or very sparse rewards, while the self-supervised and iterated-learning papers emphasize sensitivity to Rd\mathbb{R}^d27, Rd\mathbb{R}^d28, and Rd\mathbb{R}^d29 (Obando-Ceron et al., 15 Oct 2025, Lavoie et al., 2022, Ren et al., 2023).

These uses suggest that “simplicial embeddings” is not a single method but a structural principle. In topology, the principle is preservation of incidence, homology, and ambient nonintersection. In spectral and representation-learning settings, it is preservation of higher-order adjacency, harmonic circulation, or simplex-constrained barycentric structure. What remains common across the cited literature is that simplices are treated as first-class objects rather than as reducible collections of pairwise edges, and the embedding is designed to retain that higher-order organization in the target space.

Topic to Video (Beta)

No one has generated a video about this topic yet.

Whiteboard

No one has generated a whiteboard explanation for this topic yet.

Follow Topic

Get notified by email when new papers are published related to Simplicial Embeddings.